CHAPTER 8 EXPERIMENTAL DESIGN. CONFOUNDING AND INTERNAL VALIDITY Confounding Variable: confounding...

CHAPTER 8CHAPTER 8

EXPERIMENTAL DESIGN

CONFOUNDING AND CONFOUNDING AND INTERNAL VALIDITYINTERNAL VALIDITY

Confounding Variable: confounding occurs when the effects of the independent variable and an uncontrolled variable are intertwined so one cannot determine which is responsible for the effect

CONFOUNDING AND CONFOUNDING AND INTERNAL VALIDITYINTERNAL VALIDITY

Internal Validity: experiment must be designed and conducted so that only the independent variable can be the cause of the results

BASIC EXPERIMENTSBASIC EXPERIMENTS

Posttest-Only DesignMust:

Obtain two equivalent groups of participantsSelection differences

Introduce the independent variableMeasure the effect of the independent variable on

the dependent variable

POSTTEST-ONLY DESIGNPOSTTEST-ONLY DESIGN

BASIC EXPERIMENTSBASIC EXPERIMENTS

Pretest-Posttest DesignA pretest is given before the experimental

manipulation is introduced to make sure groups are equivalent at the beginning of the experiment

BASIC EXPERIMENTSBASIC EXPERIMENTS

Advantages of the pretest-posttest designMortality (dropout factor)Assess equivalency of groups with small

sample sizeCan use to select participants for the

experiment

BASIC EXPERIMENTSBASIC EXPERIMENTS

• Disadvantages of the pretest-posttest design• Time consuming• Sensitize participants to what is being studied

- Demand characteristics

- Reduces external validity

ASSIGNING PARTICIPANTS ASSIGNING PARTICIPANTS EXPERIMENTAL CONDITIONSEXPERIMENTAL CONDITIONS

Independent Groups DesignParticipants participate in only one group

Repeated Measures DesignParticipants Are in All Conditions

REPEATED MEASURES DESIGNREPEATED MEASURES DESIGN

Advantages and Disadvantages of Repeated Measures DesignAdvantages

Fewer participantsExtremely sensitive to statistical differencesConditions are identical because person is own control group

DisadvantagesOrder effect

- Practice effect- Fatigue effect- Contrast effect

REPEATED MEASURES DESIGNREPEATED MEASURES DESIGN

CounterbalancingTime Interval Between Treatments

COUNTERBALANCINGCOUNTERBALANCING

MATCHED PAIRS DESIGNMATCHED PAIRS DESIGN

Goal is to Match People on a Participant Characteristic

Either the Dependent Measure or a Variable that is Strongly Related to the Dependent Variable

Analysis of Covariance