Chapter 12 Experimental Research

7/28/2019 Chapter 12 Experimental Research

1/43

Experimental Research

121


2/43

1. Identify the independent variable, dependent variable, and construct a valid

simple experiment to assess a cause and effect relationship

2. Understand and minimize experimental error3. Know ways of minimizing experimental demand characteristics

4. Avoid unethical experimental practices

5. Understand the advantages of a between-subjects experimental design

6. Weigh the trade-off between internal and external validity

7. Use manipulations to implement a completely randomized experimentaldesign, a randomized-block design, and a factorial experimental design

LEARNING OUTCOMES

12

2

After studying this chapter, you should be able to


3/43

Subjects The sampling units for an experiment,

usually human respondents who provide

measures based on the experimental

manipulation.

Independent Variables

Experimental conditions

One of the possible levels of an

experimental (independent) variable

manipulation.

Blocking variables

Variables included in the statistical

analysis as a way of controlling or

accounting for variance due to that

variable:

Categorical variables

12

3


4/43

EXHIBIT 12.1 Experimental Conditions in Self-Efficacy Experiment

12

4


5/43

Main Effect

The experimental difference in dependent variable means between the different levels of any single

experimental variable.

Interaction Effect

Differences in dependant variable means due to a specific combination of independent variables.

12

5


6/43

EXHIBIT 12.2 Job Satisfaction Means in Self-Efficacy Experiment

12

6


7/43

EXHIBIT 12.3 Experimental Graph Showing Results within Each Condition

12

7


8/43

Manipulation of the Independent Variable

Experimental treatment: the way an experimental variable is manipulated.

Categorical variables: described by class or quality

Continuous variables: described by quantity (level)

Experimental Group

A group of subjects to whom an experimental treatment is administered.

Control Group A group of subjects to whom no experimental treatment is administered.

12

8


9/43

More than One Independent

Variable

Cell: a specific treatment combination

associated with an experimental group.

Computation of the

number of cells in an

experiment:K= (T1)(T2)..(Tm)

Repeated Measures

Experiments in which an individual

subject is exposed to more than one level

of an experimental treatment.

12

9


10/43

Selection and Measurement of the

Dependent Variable

Selecting dependent variables that are

relevant and truly represent an outcome

of interest is crucial.

Choosing the right dependent variable is

part of the problem definition process.

Thorough problem definition will help

the researcher select the most

important dependent variable(s).

1210


11/43

Selection and Assignment of TestUnits

Test units: the subjects or entities whose

responses to treatment are measured or

observed.

Sample Selection And Random

Sampling Errors Systematic or nonsampling error

Subject selection, experimental design,

and unrecognized extraneous variables

Overcoming sampling errors

Randomization

Matching Control over extraneous variables

1211


12/43

Sample Selection And RandomSampling Errors

Experimental Confound

When there is an alternative

explanation beyond the experimental

variables for any observed differences

in the dependent variable.

Once a potential confound is identified,

the validity of the experiment is

severely questioned.

Extraneous variables

Variables that naturally exist in the

environment that may have some

systematic effect on the dependentvariable.

1212


13/43

Demand Characteristic

An experimental design element or

procedure that unintentionally provides

subjects with hints about the research

hypothesis.

Demand Effect Occurs when demand characteristics

actually affect the dependent variable.

Hawthorne Effect

People will perform differently from

normal when they know they are

experimental subjects.

1213


14/43


15/43

Constancy of Conditions

Subjects in all experimental groups are

exposed to identical conditions except for

the differing experimental treatments.

Counterbalancing

Attempts to eliminate the confounding

effects of order of presentation by varying

the order of presentation (exposure) of

treatments to subject groups.

1215


16/43

Debriefing experimental subjects

Communicating the purpose of the

experiment

Explaining the researchers hypotheses

Attempts to interfere with acompetitors test-marketing efforts

Such acts as changing prices or increasing

advertising to influence (confound)

competitors test-marketing results are

ethically questionable.

12

16


17/43

Basic versus FactorialExperimental Designs Basic experimental designs a

single independent variableand a single dependentvariable.

Factorial experimental designallows for an investigation ofthe interaction to two or moreindependent variables.

Laboratory Experiment A situation in which the

researcher has more completecontrol over the researchsetting and extraneousvariables.

Field Experiments Research projects involving

experimental manipulationsthat are implemented in anatural environment.

12

17


18/43

EXHIBIT 12.5 The Artificiality of Laboratory versus Field Experiments

12

18


19/43

Within-Subjects Design

Involves repeated measures because with each treatment the same subject is measured.

Between-Subjects Design

Each subject receives only one treatment combination.

Usually advantageous although they are usually more costly.

Validity is usually higher.

12

19


20/43

EXHIBIT 12.6

Within- and

Between-

Subjects

Designs

12

20


21/43

Internal Validity

The extent that an experimental variable

is truly responsible for any variance in the

dependent variable.

Does the experimental manipulation

truly cause changes in the specificoutcome of interest?

Manipulation Checks

A validity test of an experimental

manipulation to make sure that the

manipulation does produce differences in

the independent variable.

12

21


22/43

12

22

InternalValidity

Maturation

Testing

InstrumentationSelection

Mortality

History


23/43

History Effect

Occurs when some change other than the

experimental treatment occurs during the

course of an experiment that affects the

dependent variable.

Cohort Effect

A change in the dependent variable

that occurs because members of one

experimental group experienced

different historical situations than

members of other experimental

groups.

12

23


24/43

Maturation Effects

Effects that are a function of time and the

naturally occurring events that coincide

with growth and experience.

Testing effects

A nuisance effect occurring when the

initial measurement or test alerts or

primes subjects in a way that affects their

response to the experimental treatments.

12

24


25/43

Instrumentation Effect

A change in the wording of questions, a

change in interviewers, or a change in

other procedures causes a change in the

dependent variable.

Selection

The selection effect is a sample bias thatresults from differential selection of

respondents for the comparison groups,

or a sample selection error.

Mortality Effect (Sample Attrition)

Occurs when some subjects withdraw

from the experiment before it is

completed.

12

25


26/43

12

26

HistoryUncontrollable events occurring inthe environment between beforeand after measurements

MaturationChanges in subjects during thecourse of the experiment

TestingA before measure that alerts orsensitizes subject to the nature ofexperiment or second measure.

A major employer closes its plantin test market area.

Subjects become tired during theexperiment.

A questionnaire about thetraditional role of womentriggers enhanced awareness offemales in an experiment.

Extraneous Variable Example


27/43

12

27

Instrument Changes in instrument result inresponse bias

SelectionSample selection error because ofdifferential selection comparisongroups

MortalitySample attrition; some subjectswithdraw from experiment

New questions about women areinterpreted differently from earlierquestions.

Control group and experimentalgroup is self-selected group basedon preference for soft drinks

Subjects in one group of a hairdying study marry rich widows andmove to Florida

Extraneous Variable Example


28/43

External Validity

The accuracy with which experimental

results can be generalized beyond the

experimental subjects.

Student surrogates: Atypical?

Trade-Offs Between Internal andExternal Validity

Artificial laboratory experiments usually

are high in internal validity, while

naturalistic field experiments generally

have less internal validity, but greater

external validity.

12

28


29/43

1229

Laboratory

Experiment

Field

Experiment

Artificial: Low Realism

Few Extraneous

Variables

High control

Low Cost

Short Duration

Subjects Aware of

Participation

Natural: High Realism

Many Extraneous

Variables

Low control

High Cost

Long Duration

Subjects Unaware of

Participation


30/43

Basic Experimental Design An experimental design in which only one

variable is manipulated.

Diagramming Experimental

Designs: Symbols

1230


31/43

Quasi-experimental Designs

Experimental designs that do not involve

random allocation of subjects to

treatment combinations.

One Shot Design (AfterOnly):

X

O1

One Group Pretest

Posttest:

O1X

O2

Static Group

Design:

ExperimentalX

O1

Control

O2

1231


32/43

PretestPosttest

Control Group Design

(BeforeAfter withControl)

Experimental

R O1 X O2

Control

R O3 X O4

Posttest Only Control

Group

(After-Only with

Control)

Experimental

R X O1 Control

R O2

1232


33/43

EXHIBIT 12.7 Product Preference Measure in an Experiment

1233


34/43

EXHIBIT 12.8

Selected Time Series

Outcomes

1234


35/43

1235

CompletelyRandomized

Design

Randomized BlockDesign

Factorial


36/43

Completely Randomized Design

An experimental design that uses a random

process to assign subjects (test units) to

treatment levels to investigate the effects of an

experimental variable.

1236


37/43

Randomized Block Design

An extension of the completely

randomized design in which a single

categorical extraneous variable that might

affect test units responses to the

treatment is identified and the effects of

this variable are isolated by being blocked

out.

Blocking Variable

A categorical variable that is expected to

be associated with different values of a

dependent variable for each group. It

effectively controls for an extraneous

cause in experimental analysis.

1237


38/43

EXHIBIT 12.9 Randomized Block Design

1238


39/43

Factorial Design

An experiment that investigates theinteraction of two or more independent

variables on a single dependent variable.

1239


40/43

EXHIBIT 12.10 Factorial DesignSalary and Vacation

1240


41/43

Main effect

The influence of a single independent

variable on a dependent variable.

Interaction effect

The influence on a dependent variable by

combinations of two or more

independent variables.

Interaction occurs if the effect of one

treatment differs at various levels of the

other treatment.

1241


42/43

EXHIBIT 12.11 A 2 2 Factorial Design That Illustrates the Effects of Sex and Ad Content on

Believability

1242


43/43

EXHIBIT 12.12 Graphic Illustration of Interaction between Gender and Advertising Copy

12

Documents

Chapter 12 Experimental Research