1. Between-Subjects Experimental Designs
Chapter 10
Between-Subjects Experimental Designs

2. Chapter Outline Conducting experiments: Between-subjects design
Experimental versus control group
Manipulation and the independent variable
Variability and the independent variable
Ethics in Focus: The accountability of manipulation
Comparing two independent samples
Comparing two or more independent samples
Measuring the dependent variable
Advantages and disadvantages of the between-subjects design

3. Conducting Experiments: Between-Subjects Design
Between-subjects design – Different participants are observed one time in each group or at each level of a factor
Between-subjects experimental design – Levels of a between-subjects factor are manipulated, then different participants are randomly assigned to each group or to each level of that factor, and observed one time
Between-subjects factor: Type of factor in which different participants are observed in each group, or at each level of the factor

4. Conducting Experiments: Between-Subjects Design
Control: (a) the manipulation of a variable and (b) holding all other variables constant
Experimental or treatment group: Participants are treated or exposed to a manipulation, or level of the IV, that is believed to cause a change in the DV
Control group: Participants are treated the same as those in an experimental group, except that the manipulation is omitted
Placebo: An inert substance, surgery, or therapy that resembles a real treatment but has no real effect

5. Conducting Experiments: Between-Subjects Design

6. Manipulation and the Independent Variable
Experimental manipulation – The identification of an IV and the creation of two or more groups that constitute the levels of that variable
Natural manipulation: Manipulation of a stimulus that can be naturally changed with little effort
Typically involves manipulation of a physical stimulus
Ex. Dimmed or brightly lit room, soft or loud sounds
Staged manipulation: Manipulation of an IV that requires the participant to be “set up” to experience some stimulus or event
Often requires the help of a confederate
Confederate: Coresearcher in cahoots with the researcher

7. Manipulation and the Independent Variable

8. Manipulation and the Independent Variable
Random assignment and control
Random assignment: Procedure used to ensure that each participant has the same likelihood of being selected to a given group
Can be confident that any differences observed between groups can be attributed to the different levels of the IV and not individual differences
Advantages: It makes the individual differences of participants about the same in each group, ensures that participants and individual differences of participants are assigned to groups entirely by chance

9. Manipulation and the Independent Variable
Restricted measures of control
Restricted random assignment: Restricting a sample based on known participant characteristics, then using a random procedure to assign participants to each group
Control by matching: Assess or measure the characteristic we want to control, group or categorize participants based on scores on that measure, and then use a random procedure to assign participants from each category to a group in the study
Control by holding constant: Limit which participants are included in a sample based on characteristics they exhibit that may otherwise differ between groups in a study

10. Manipulation: Control By Matching

11. Variability and the Independent Variable
As an added measure of control, we can also measure individual differences numerically in terms of error variance
Error variance or error: Numeric measure of the variability in scores that can be attributed to or is caused by the individual differences of participants in each group
Random variation is measured by determining the extent to which scores in each group overlap
The more the scores overlap, the larger the error variance
The less the scores overlap, the smaller the error variance
Test statistic: Mathematical formula that allows researchers to determine the extent to which differences observed between groups can be attributed to the manipulation used to create the different groups

12. Overlap and Identifying Error

13. Ethics in Focus: The Accountability of Manipulation
Because the researcher creates or manipulates the levels of an IV in an experiment, he or she bears greater responsibility for how participants are treated in each group
Manipulating the levels of an IV can be associated with greater ethical accountability on the part of the researcher

14. Comparing Two Independent Samples
Selecting Two Independent Samples
Independent sample: Different participants are independently observed one time in each group

15. Comparing Two Independent Samples
The use of the test statistic
Once participants have been assigned to groups, conduct the experiment and measure the same DV in each group
To compare differences between groups, compute a test statistic, which is a mathematical formula that allows us to determine whether the manipulation or error variance is likely to explain differences between the groups
Two-independent sample t test: Used to test hypotheses concerning the difference in interval or ratio scale data between two group means, in which the variance in the population is unknown
t = Mean differences between groups
Mean differences attributed to error

16. Comparing Two or More Independent Samples
Selecting multiple independent samples

17. Comparing Two or More Independent Samples
The use of the test statistic
One-way between subjects ANOVA: Used to test hypotheses for one factor with two or more levels concerning the variance among group means
Used when different participants are observed at each level of a factor and the variance in a given population is unknown
F = variability between groups
variability attributed to error
Post hot test: Computed following a significant ANOVA to determine which pair(s) of group means significantly differ
These tests are needed with more than two groups because multiple comparisons must be made
Pairwise comparison: Statistical comparison for the difference between two group means

18. Measuring the Dependent Variable
Self report measure – Participants respond to one or more questions or statements to indicate their actual or perceived experiences, attitudes, or opinions
Responses can be coded numerically or given on numeric response scales
Behaviors can be measured using a single item or many behaviors can be measured using multiple-item surveys
Advantages: Easy and cost-effective to administer, allows researchers to measure a lot of data in a little time
Disadvantage: Self-report items are often inaccurate

19. Measuring the Dependent Variable
Behavioral measure – Researchers directly observe and record the behavior of subjects or participants
How we measure the behavior observed mostly depends on how the behavior is operationalized
Ex. To test a hypothesis about eating behavior, we could measure how much people eat, how quickly people eat, or how often people eat
Advantage: A more direct measure than self-reported behavior
Disadvantages: Can require substantial ethical problems, some aspects of behavior are constructs that do not have obvious behavioral measures

20. Measuring the Dependent Variable
Physiological measure – Researchers record physical responses of the brain and body in a human or an animal
The normal and disordered functioning of the physiological responses of participants can be compared between groups in an experiment
Ex. Measure stress and anxiety by measuring cortisol levels in a blood sample or by measuring galvanic skin response (GSR)
Advantages: When careful collection procedures are used, these measures are unbiased
Disadvantages: Expense and training to operate the equipment needed to make measurements

21. Advantages and Disadvantages of the Between-Subjects Design
It is the only design that can meet all three requirements of an experiment (randomization, manipulation, inclusion of a comparison/control group)
Places less of a burden on the participant and the researcher
Disadvantages
Sample size required can be large, particularly with many groups

22. Within-Subjects Experimental Designs
Chapter 11
Within-Subjects Experimental Designs

23. Chapter Outline Conducting experiments: Within-subjects design
Controlling time-related factors
Ethics in Focus: Minimizing participant fatigue
Individual differences and variability
Comparing two related samples
Comparing two or more related samples
An alternative to pre-post designs: Solomon four-group design
Comparing between-subjects and within-subjects designs

24. Conducting Experiments: Within-Subjects Design
Within-subjects design, also called a repeated-measures design – Design in which the same participants are observed one time in each group of a research study
Within-subjects experimental design – The levels of a within-subjects factor are manipulated, then the same participants are observed in each group or at each level of the factor
To qualify as an experiment, the researcher must (1) manipulate the levels of the factor and include a comparison/control group, and (2) make added efforts to control for order and time-related factors
Within-subjects factor: Type of factor in which the same participants are observed in each group, or at each level of the factor

25. Conducting Experiments: Within-Subjects Design
Two common reasons that researchers observe the same participants in each group are as follows:
1. To manage sample size
2. To observe changes in behavior over time, which is often the case for studies on learning or within–participant changes over time
The within-subjects experimental design does not meet the randomization requirement for demonstrating cause and effect
Because the participants are observed in each group, we cannot use random assignment, therefore do not use randomization

26. Conducting Experiments: Within-Subjects Design

27. Controlling Time-Related Factors
Time-related factors must be controlled or made the same between groups, such that only the levels of the IV are different between groups
Time related factors include those introduced in chapter 6, such as maturation, testing effect, regression toward the mean, and attrition
Participant fatigue: State of physical or psychological exhaustion resulting from intense research demands typically due to observing participants too often, or requiring participants to engage in research activities that are too demanding

28. Controlling Time-Related Factors
To control for time-related factors, researchers make efforts to control for order effects
Order effects: A threat to internal validity in which the order in which participants receive different treatments or participate in different groups causes changes in a DV
Carryover effects: A threat to internal validity in which participation in one group “carries over” or causes changes in performance in a second group
Two strategies to control for order effects are to control order and control timing

29. Controlling Time-Related Factors
Counterbalancing – The order in which participants receive different treatments or participate in different groups is balanced or offset in an experiment
1. Complete counterbalancing: A procedure in which all possible order sequences in which participants receive different treatments or participate in different groups are balanced or offset in an experiment
Used when the number of treatments or different groups is small, usually two groups but not more than three
To calculate, make the following calculation in which k is the number of treatments or groups:
Number of possible order sequences = k!

30. Controlling Time-Related Factors
2. Partial counterbalancing: A procedure in which some, but not all, possible order sequences in which participants receive different treatments or participate in different groups are balanced or offset in an experiment
Often used when there are three or more groups
To ensure that the few counterbalanced order sequences are representative of all order sequences, we must ensure:
Each treatment or group appears equally often in each position
Each treatment or group precedes and follows each treatment or group one time
Latin square: A matrix design in which a limited number of order sequences are constructed such that (1) the number of order sequences equals the number of treatments, (2) each treatment appears equally often in each position, and (3) each treatment precedes and follows each treatment one time

31. Controlling Time-Related Factors

32. Controlling Time-Related Factors
Interval between treatments or groups
We control the interval to minimize possible testing and carryover effects
Often need to increase the interval between treatments when a treatment causes physiological arousal, such as exercise
Total duration of an experiment
We control the total duration to minimize the total demands placed on participants, which, when great, can lead to participant attrition, or fatigue

33. Ethics in Focus: Minimizing Participant Fatigue
Researchers must disclose any potential risks, including those related to participant fatigue
To minimize risks:
Minimize the duration needed to complete the experiment
Allow for a reasonable time interval or rest period between treatment presentations

34. Individual Differences and Variability
The within-subjects design minimizes individual differences between groups because the same participants are observed in each group
When the same participants are observed in each group, the individual differences of participants are also the same in each group

35. Individual Differences and Variability
Sources of variability
Between-groups variability: Source of variance in a dependent measure that is caused by or associated with the manipulation of the levels (or groups) of an IV
This variability is measured by the group means

36. Individual Differences and Variability
Within-groups variability: Source of variance in a dependent measure that is caused by or associated with observing different participants within each group
Between-persons variability: Source of variance in a dependent measure that is caused by or associated with individual differences or differences in participant responses across all groups
Assume this is equal to zero in a within-subjects design because the same participants are observed in each group
These sources of variation are called error
Error: Source of variance that cannot be attributed to having different groups or treatments
Error = Within-Groups Variability + 0

37. Individual Differences and Variability

38. Comparing Two Related Samples
The goal in experimentation is to minimize the possibility that individual differences, or something other than a manipulation, caused differences between groups

39. Comparing Two Related Samples
Selecting two related samples
Related sample, also called a dependent sample: The same or matched participants are observed in each group
There are two ways to select two related samples:
1. The same participants are observed in each group
2. Participants are matched, experimentally or naturally, based on the common characteristics or traits that they share

40. Comparing Two Related Samples
1. The same participants are observed in each group
We can select one sample from one population and observe that one sample of participants in each group
This type of sampling, used with a repeated- measures design, can be used in an experiment only if we manipulate the levels of the IV and control for order effects

41. Comparing Two Related Samples
2. Matched-samples design – A within- subjects research design in which participants are matched, experimentally or naturally, based on preexisting characteristics or traits that they share
Cannot be used in an experiment because groups are created based on preexisting characteristics and not on a manipulation made by the researcher

42. Comparing Two Related Samples
The use of the test statistic
Test statistic: Mathematical formula that allows us to determine whether the manipulation or error variance is likely to explain differences between the groups
Related-samples t test, also called a paired- samples t test: Statistical procedure used to test hypotheses concerning the difference in interval or ratio scale data for two related samples in which the variance in one population is unknown
t = Mean differences between groups
Mean differences attributed to error

43. Comparing Two Related Samples

44. Comparing Two or More Related Samples
Selecting multiple related samples
Only the repeated-measures design can be used to observe participants in more than two groups

45. Comparing Two or More Related Samples
The use of the test statistic
One-way within-subjects analysis of variance (ANOVA): Statistical procedure used to test hypotheses for one factor with two or more levels concerning the variance among group means. This test is used when the same participants are observed at each level of a factor and the variance in a given population is unknown
F = Variability between groups
Variability attributed to error
The one-way within-subjects ANOVA informs us that at least one group is different from another group – it does not tell us which pairs of groups differ
We compute post hoc tests when we have more than two groups

46. Comparing Two or More Related Samples

47. An Alternative to Pre-Post Designs: Solomon Four-Group Design
Solomon four-group design – Experimental research design in which different participants are assigned to each of four groups in such a way that comparisons can be made to:
(1) determine if a treatment causes changes in posttest measure
(2) control for possible confounds or extraneous factors related to giving a pretest measure and observing participants over time

48. An Alternative to Pre-Post Designs: Solomon Four-Group Design
To apply the Solomon four-group design, participants are randomly assigned to one of four groups:

49. An Alternative to Pre-Post Designs: Solomon Four-Group Design
A strength is that multiple comparisons can be made
Comparison 1: Difference in pretest-posttest scores for Group A compared to difference in pretest-posttest scores for Group B
Comparison 2 (control): Group A posttest and Group C posttest comparison
Comparison 3 (control): Group B pretest and Group D posttest
Comparison 4 (control): Group B posttest and Group D posttest
Comparison 5 (control): Difference in posttest scores for Groups C and D compared to posttest scores for Groups A and B
Another strength is that a within-subjects design (pre-post comparisons) is combined with a between-subjects design (between-group comparisons) to establish control
Main limitation is the complexity of the design

50. Comparing Between-Subjects and Within-Subjects Designs
Between-subjects design: Randomization
The between-subjects design allows researchers to randomly assign participants to groups or to the levels of an IV
Advantage of using random assignment is that it makes individual differences about the same in each group
Another advantage is that participants are observed one time in one group

51. Comparing Between-Subjects and Within-Subjects Designs
Within-subjects design: Economizing and power
The advantage of using a within-subjects design is that fewer participants are required overall
The second advantage is that the test statistic has greater power to detect significant differences
We can represent the test statistic for each experimental design as follows:
Between-subjects design: differences or variance between groups
within-groups + between- persons error
Within-subjects design: differences or variance between groups
within-groups error