1. Experiments with Two Groups
Ryan M. Denney, Ph.D.
The University of Southern Mississippi
PSY 361

2. Two-Group Designs Experimental design
The general plan for selecting participants, assigning participants to experimental conditions, controlling extraneous variables, and gathering data.
Principle of parsimony (Occam’s razor)
The belief that explanations of phenomena and events should remain simple until the simple explanations are no longer valid.
The simplest explanation or strategy tends to be the best one

3. Two-Group Designs Independent variable (IV) Dependent variable (DV)
A stimulus or aspect of the environment that the experimenter directly manipulated to determine its influences on behavior.
Dependent variable (DV)
A response or behavior that is measured. It is desired that changes in the DV be directly related to manipulation of the IV.
Levels of the IV
The most common manner of creating two groups with one IV is to present some amount or type of IV to one group and to withhold that IV from the second group.
Thus, the presence of the IV is contrasted with the absence of the IV.
These differing amounts of the IV are referred to as the levels of the IV.

4. Two-Group Designs Experimental group Control group
In a two-group experimental design, the group of participants that receives the IV/treatment.
Control group
In a two-group experimental design, the group of participants that does not receive the IV.
The simplest way to find out whether our IV caused a change in behavior is to compare research participants who have received the IV to others who have not
If those two groups differ, and we are assured that we controlled potential extraneous variables, then we conclude that the IV caused the participants to differ.

5. Two-Group Designs
Random Assignment: assigning research participants to groups so that each participant has an equal chance of being in any group
Random assignment tends to create equal groups in the long run.
As groups get larger, we can place more confidence in random assignment achieving what we want it to; that is, evenly dividing extraneous variables
Different from random selection: randomly choosing participants
Independent groups: random assignment of participants to groups
Between-subjects comparison: comparing the performance of participants in two groups
Ex: Impulse control in caffeinated vs. uncaffeinated random sample of people in Coffee Shop (compare people in both groups across age, education, SES, etc)

6. Random-shmandom
Sometimes we are concerned that random assignment may not create equal groups
Must then use “nonrandom” assignment techniques to create more equal groups
Correlated assignment—used when we have only a small number of participants to choose from and we’re concerned that random assignment may not yield equal groups
A method of assigning research participants to groups based on some relationship they have with each other. Used with small numbers of participants. (Ex: hetero couples in which the male has been exposed to partner violence)
These small groups are then randomly assigned to treatment conditions (also known as paired or matched assignment). Ex: to receive psychoed about partner violence or not—measure relationship satisfaction

7. Two-Group Designs 1. Matched Pairs
Research participants in a two-group design who are measured and equated on some variable before the experiment. (Ex: intro/extrovert)
After we have measured this variable, we create pairs of participants that are equal on this variable.
After we have created our matched pairs, we then randomly assign participants from these pairs to the different treatment conditions. (Ex: speaking to crowd)

8. Two-Group Designs Matched pairs example Flip coin: XX OO XX OO
Measure participants along some important (possibly confounding) variable
Group participants in pairs of similarity
Example: gender, northerner/southerner, SUV owner/small car owner
Flip coin: XX OO XX OO
Experimental Group: X, O, X, O
Control Group: X, O, X, O
Yields equal groups

9. Two-Group Designs 2. Repeated measures
The same participants are tested in both treatment conditions of our experiment.
The matched pairs are perfectly equal because they consist of the same people or animals tested across the entire experiment.
No extraneous variables (contained within participants) should be able to confound the results because any difference between the participants’ performance in the two treatment conditions should be due to the IV.
Participants serve as their own controls.
Impossible when you cannot completely remove the effects of the previous condition (questionnaire, memory priming)
Impossible when DV cannot be measured “purely” more than once (solving a puzzle, attitudes toward …)

10. Two-Group Designs 3. Natural pairs Within-subjects comparison
Pairs of participants are created from naturally occurring pairs (e.g. biologically or socially related).
For example, twins, siblings, parents and children, husbands and wives
Within-subjects comparison
Refers to contrasting groups of participants who were assigned through matched pairs, natural pairs, or repeated measures.
Essentially comparing scores within the same participants. (i.e., comparing each participant’s score to his/her own other score)
Although this direct comparison is literally true only for repeated-measures designs, participants in matched or natural pairs are “the same” with regard to the matching variable.
Ex: Math is Stressful: Student’s stress responses
Preteststressful calculation test (backward from 715 by 13, “most do it in 10 minutes”)posttest
Comparing subjects to themselves: controlling for: age, intelligence, time of day

11. Analyzing Two-Group Experiments
Error variability
Variability in DV scores that is due to factors other than the IV – individual differences, measurement error, and extraneous variation (also known as within- groups variability).
Goal is to maximize between-groups variability and minimize error (or within-groups) variability.
For a two-independent groups design, use a t test for independent samples to analyze your data.
For a two-correlated-groups design, analyze your data with a t test for correlated samples (a.k.a dependent t test)

12. Analyzing Two-Group Experiments
Assumptions for the t test for independent samples
Homogeneity of variance
The assumption that the variances are equal for the two (or more) groups you plan to compare statistically.
Assuming the groups do not differ significantly from each other in any important way before presentation of the IV
Heterogeneity of variance
Occurs when the variability of the two groups was not comparable or equivalent
When the groups are significantly different from each other in important ways before presentation of the IV
Violates a mathematical assumption of the t statistic
t tests are robust with regard to the assumption of homogeneity, meaning it can tolerate violations of its assumptions and still provide fairly accurate results.

13. The Point
To show that two relatively equal groups differed significantly from each other for no other reason but the IV
The goals is to say that there is a statistically significant likelihood that the differences observed between equal groups are so extreme and rare that they are most likely due to the IV (the “experimentally controlled difference” between the groups)