Upload
taylor-stevens
View
4.054
Download
4
Embed Size (px)
Citation preview
Research Methods
It is actually way more exciting than it sounds
Why do we have to learn this stuff
Psychology is first and foremost a science
Thus it is based in researchBefore we delve into how to do research you should be aware
of at least two ldquohurdlesrdquo that tend to skew our thinking
Figure 41 How Do You Know What to BelieveBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
The Need for Psychological Science
Hindsight Bias we tend to believe after learning an
outcome that we would have foreseen it the ldquoI-knew-it-all-alongrdquo phenomenon
Overconfidence we tend to think we know more than we
do WREAT WATER ETRYN ENTRY GRABE BARGE OCHSA
CHAOS
Types of Descriptive Research (aka Non-Experimental)
bullThe Case Study
bullThe Survey
bullNaturalistic Observation
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Why do we have to learn this stuff
Psychology is first and foremost a science
Thus it is based in researchBefore we delve into how to do research you should be aware
of at least two ldquohurdlesrdquo that tend to skew our thinking
Figure 41 How Do You Know What to BelieveBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
The Need for Psychological Science
Hindsight Bias we tend to believe after learning an
outcome that we would have foreseen it the ldquoI-knew-it-all-alongrdquo phenomenon
Overconfidence we tend to think we know more than we
do WREAT WATER ETRYN ENTRY GRABE BARGE OCHSA
CHAOS
Types of Descriptive Research (aka Non-Experimental)
bullThe Case Study
bullThe Survey
bullNaturalistic Observation
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Figure 41 How Do You Know What to BelieveBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
The Need for Psychological Science
Hindsight Bias we tend to believe after learning an
outcome that we would have foreseen it the ldquoI-knew-it-all-alongrdquo phenomenon
Overconfidence we tend to think we know more than we
do WREAT WATER ETRYN ENTRY GRABE BARGE OCHSA
CHAOS
Types of Descriptive Research (aka Non-Experimental)
bullThe Case Study
bullThe Survey
bullNaturalistic Observation
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
The Need for Psychological Science
Hindsight Bias we tend to believe after learning an
outcome that we would have foreseen it the ldquoI-knew-it-all-alongrdquo phenomenon
Overconfidence we tend to think we know more than we
do WREAT WATER ETRYN ENTRY GRABE BARGE OCHSA
CHAOS
Types of Descriptive Research (aka Non-Experimental)
bullThe Case Study
bullThe Survey
bullNaturalistic Observation
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Types of Descriptive Research (aka Non-Experimental)
bullThe Case Study
bullThe Survey
bullNaturalistic Observation
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Case Studiesbull An in-depth picture
of one or a few subjects
bull Tells us a great storyhellip but is just descriptive research
bull Could it be that the case is atypical
The ldquoidealrdquo case study is the Duggar family Really interesting but what does it tell us about families in general
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Survey MethodbullCheap and Fast
bullEasy Sampling
bullLow Response Rate
bullPeople Lie
bullWording Effects
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
The Problem with Surveys
(examples of the wording effect)bull ldquoignorantrdquo of what is being asked
(from the Louis Harris Poll taken at New Yorkrsquos American Museum of Natural History)
ndash77 interested in plantstrees 39 botany
ndash48 fossils 39 in paleontology
ndash42 rocksminerals 53 geology
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Naturalistic Observationbull ldquoWatchingrdquo subjects in
their natural environment
bull No manipulation of the environment
bull Negative ndash can never really show cause and effect
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Correlational Methodbull correlation
expresses a relationship between two variables
bull does NOT show causation
As more ice cream is eaten more people are murdered
Does ice cream cause murder or murder cause people to eat ice cream
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Correlative Research ndash More ProblemsIllusory Correlations
bull When we believe there is a relationship we tend to recall and notice instances that confirm our belief
bull ie ndash sugar = hyperactive children cold + wet = cold weather change = arthritis pain
bull related to Hindsight Bias
Perceiving Order in Random Events
bull assuming that certain random outcomes are morely likely than other random outcomes
bull ie ndash flipping coins hands of cards being dealt choosing lottery numbers etc
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Types of CorrelationPositive Correlationbull The variables go in
the SAME direction
Negative Correlationbull The variables go in
opposite directions
Studying and grades hopefully have a positive correlation
Heroin use and grades probably have a negative correlation
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Positive CorrelationbullAs the value of one variable increases (or decreases) so does the value of the other variablebullA perfect positive correlation is +10bullThe closer the correlation is to +10 the stronger the relationship
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Negative Correlation
bullAs the value of one variable increases the value of the other variable decreasesbullA perfect negative correlation is -10bullThe closer the correlation is to -10 the stronger the relationship
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
How to Read a Correlation Coefficient
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Correlation Coefficientbull A number that
measures the strength of a relationship
bull Range is from -1 to +1
bull The relationship gets weaker the closer you get to zero
Which is a stronger correlation
HINT remember ldquoabsolute valuerdquo)
bull -13 or +38bull -72 or +59bull -91 or +04
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Figure 42 Positive and Negative CorrelationsBlair-Broeker and Ernst Thinking About Psychology Second EditionCopyright copy 2008 by Worth Publishers
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Correlation Practice
bullIQacademic successbullSelf esteemdepressionbullStresshealthbullShoe size grade on next exambullEducationincomebullPrice of gassales of SUVrsquos
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Experimental Methodbull Looking to prove
causal relationships
bull Cause Effectbull Laboratory v Field
Experiments Smoking causes health issues
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Research Vocabulary
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Hypothesisbull Expresses a
relationship between two variables
bull A variable is anything that can vary among participants in a study
bull Participating in class leads to better grades than not participating
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Independent Variableaka the ldquocauserdquo
bull Whatever is being manipulated in the experiment
bull Hopefully the independent variable brings about change If there is a drug in
an experiment the drug is almost always the independent variable
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Dependent Variablethe ldquoeffectrdquo
The dependent variable would be the effect of the drug
bull Whatever is being measured in the experiment
bull It is dependent on the independent variable
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Identifying Independent and Dependent Variables
1 Developmental psychologists want to know if exposing children to public television improves their reading skills
2 Behavioral psychologists want to know whether reinforcing comments will make people work harder on an assembly line
3 A clinical psychologist wants to know whether people who have psychotherapy are more or less likely to have problems in the future
4 A social psychologist wants to know whether being polite or rude to people tends to make them more cooperative
5 A personality psychologist explores whether extroverted people have more fun at parties
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Experimental VocabularybullPopulation the group from which your participants were drawn from
bullExperimental Group Group exposed to IV
bullControl Group Group not exposed to IV
bullReplication to repeat an experiment usually with different participants in different situations
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Operational Definitionsbull Explain what you
mean in your hypothesis
bull How will the variables be measured in ldquoreal liferdquo terms
bull How you operationalize the variables will tell us if the study is replicable
Letrsquos say your hypothesis is that chocolate causes violent behavior
bull What do you mean by chocolate
bull What do you mean by violent behavior
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
1The teacher wants to find a way to help make Billy act more friendly toward the other children
2 A psychologist wants to know if his new form of psychotherapy will make people less depressed
3 College athletes are not as smart as regular students
4 Overall senior girls are prettier than junior girls
5 The school spirit is at an all-time low
How might we operationally define the following
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Samplingbull Identify the
population you want to study
bull The sample must be representative of the population you want to study
bull GET A RANDOM SAMPLE
bull Stratified Sampling
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Beware ofConfounding Variables
If I wanted to prove that smoking causes heart issues what are some confounding variables
bull The object of an experiment is to prove that A causes B
bull A confounding variable is anything that could cause change in B that is not A
Lifestyle and family history may also effect the heart
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Experimenter Biasbull Another
confounding variable
bull Not a ldquoconsciousrdquo act
bull Double-blind procedure can be used to minimizeeliminate it
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Another Confounding Variable
bull Placebo EffectndashParticipantsrsquo
expectations that the ldquotreatmentrdquo will cause the hypothesized effect
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Random Selectionamp Random Assignment
bull Once you have a random sample randomly assigning them into two groups helps control for confounding variables
bull Experimental Group v Control Group
bull Group Matching
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Blind procedurebullAn experimental procedure where the research participants are ignorant (blind) to the expected outcome of the experimentbullSometimes called single blind procedure
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Double Blind ProcedurebullA research procedure in which
both the data collectors and the research participants do not
know the expected outcome of the experiment
bullBoth groups are ignorant (blind) to the experimentrsquos purpose or
expected results
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Statisticsbull Recording the
results from our studies
bull Must use a common language so we all know what we are talking about
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Descriptive Statisticsbull Just describes sets
of databull You might create a
frequency distribution
bull Frequency polygons or histograms
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Analyze Results
bullUse measures of central tendency
mean ndash aka ldquothe averagerdquo median ndash aka ldquothe middlerdquo mode ndash aka ldquothe most commonrdquo
bullUse measures of variation (range and standard deviation)
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Central Tendency Measures
$25000-Pam $25000- Kevin
$25000- Angela$100000- Andy
$100000- Dwight
$200000- Jim$300000- Michael
Letrsquos look at the salaries of the employees at Dunder Mifflen Paper in Scranton
Median Salary - $100000Mean Salary - $110000Mode Salary - $25000
Maybe not the best place to work
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Normal Distributionbull In a normal
distribution the mean median and mode are all the same
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Normal Distribution
go back
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
A Skewed Distribution
Are the results positively or negatively skewed
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Distributionsbull Outliers skew
distributionsbull If group has one
high score the curve has a positive skew (contains more low scores)
bull If a group has a low outlier the curve has a negative skew (contains more high scores)
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Measures of Variancebull Range distance from
highest to lowest scores
bull Standard Deviation the average variance of scores from the mean
bull The higher the variance or SD the more spread out the distribution is
bull Do scientists want a big or small SD
Shaq and Kobe may both score 30 ppg (same mean)
Their SDs are very different
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
What does Standard Deviation tell us
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Inferential Statisticsbull The purpose is to
discover whether the finding can be applied to the larger population from which the sample was collected
bull P-value= 05 for statistical significance
bull 5 likely the results are due to chance
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
APA (American Psychological Association)
Ethical Guidelines for Researchbull IRB - Internal Review Boardbull For Humans and Animals
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Animal Research
bull Clear Purpose Needed
bull Treat in a Humane Way
bull Acquire Animals Legally
bull Least Amount of Suffering Possible
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief
Human Researchbull Informed Consentbull Protect from Harm
and Discomfortbull Confidentialitybull Must Debrief