1. EXPERIMENTAL PSYCHOLOGY
Alla Chavarga
Tuesdays 9:00-11:20am 2412J
or 6:10-8:30pm 432-IA
LABS:
MW 6:10-9:45pm 3106J Kravitz  MW 6:10-9:45pm 4109J Ergun  TR 11:30-3:05pm 3106J Fein  TR 11:30-3:05pm 4109J Hazan

2. Single Factor Designs CHAPTER 4 What is a factor?
Lecture Outline
What is a factor?
Types of single-factor designs with two levels
Single factor designs with more than two levels
Special purpose control group designs

3. AN EXAMPLE OF AN EXPERIMENT
An education researcher believes that watching YouTube videos can be helpful to students taking college-level mathematics courses. He plans an experiment in which he assigns students randomly to two classes: Math 101 taught in the traditional fashion, and Math 101 with YouTube video assignments. He teaches the courses for the duration of one semester in their respective styles, and gives the same final exam at the end. He then compares the average final exam score between the two classes.
What is the independent variable?
What is the dependent variable?
The independent variable is class and there are 2 levels:
Traditional math class
YouTube-based math class

4. AN EXAMPLE OF AN EXPERIMENT
An education researcher believes that the type of room in which a class takes an exam will affect their performance. He takes his PSYC1000 class and divides them into three groups: one group takes their midterm in a brightly-lit new classroom with ergonomic chairs and air conditioning; another group takes their midterm in a basement classroom with no windows, a leaky ceiling, and no AC; and the third group takes their exam in the comfort of their own home. He then compares the midterm scores.
What is the independent variable?
What is the dependent variable?
The independent variable is test environment and there are 3 levels:
Sunny, modern, comfortable room
Hot basement dungeon
Home

5. WHAT IS A FACTOR? A factor is an independent variable.
It represents the variable you think is affecting some measure.
For example:
I believe that TV watching affects violence.
I believe that type of lighting in a room and the color of the test paper affect scores.

6. SINGLE FACTOR: TWO LEVELS
Between-Subjects, Single-Factor Design
Independent Groups Design
Manipulated independent variable
Random assignment to create equivalent groups 01
Matched-Groups Design
Manipulated independent variable
Matching to create equivalent groups 02
Nonequivalent Groups Design
Subject variable as independent variable
Deliberately select participants to reduce nonequivalence 03

7. SINGLE FACTOR: TWO LEVELS
Within-Subjects, Single-Factor Design
Repeated-Measures Design
Manipulated independent variable
All participants experience all levels of experiment 01

8. ANALYZING SINGLE-FACTOR TWO-LEVEL DESIGNS
t-test assumptions
Interval or ratio-scale data
Data normally distributed
Homogeneity of variance
t-test for independent samples
Independent-groups and nonequivalent groups designs 01
t-test for paired samples / repeated measures
Within-subjects and matched-group designs 02

9. Are two levels enough? 1 2 Between subjects Multi-level designs
Advantage: ability to discover nonlinear effects 1 2
What is your impression of the effect of caffeine on RT if you are looking at graph 1?
How does this change looking at graph 2?

10. The importance of schemas for memory: Bransford & Johnson (1972)
Are two levels enough?
Another advantage of multi-level designs: ability to rule out alternative explanations
The importance of schemas for memory: Bransford & Johnson (1972)
If the balloons popped, the sound wouldn’t be able to carry, since everything would be too far away from the correct floor. A closed window would also prevent the sound from carrying, since most buildings tend to be well insulated. Since the whole operation depends on a steady flow of electricity, a break in the middle of the wire would also cause problems. Of course, the fellow could shout, but the human voice is not loud enough to carry that far. An additional problem is that a string could break on the instrument. Then there could be no accompaniment to the message. It is clear that the best situation would involve less distance. Then there would be fewer potential problems. With face to face contact, the least number of things could go wrong. (Bransford & Johnson, 1972, p. 392)

11. SINGLE FACTOR WITH MORE THAN TWO LEVELS
Full context sketch Partial context sketch
FIVE CONDITIONS
No context 1 rep
No context 2 reps
Context before
Context after
Partial context

12. SINGLE FACTOR WITH MORE THAN TWO LEVELS
Context before condition performed better than all others; the remaining conditions performed equally poorly
Evidence that this is not a practice effect (otherwise no-context 2 reps would do as well as with-context conditions)
Context must be available when encoding memory
Context must be structured correctly, otherwise “partial” condition would do well
Bransford & Johnson (1972)

13. Within-subjects, more than two levels example: The Mozart Effect
SINGLE FACTOR, MORE THAN TWO LEVELS
Within-subjects, more than two levels example: The Mozart Effect
Independent Variable – listening experience
Mozart
Gentle rainstorm
Control: no listening
Dependent variable – recall of digits (or some cognitive task)
Results
Overwhelmingly null results: no “Mozart Effect”
Significant practice effects instead

14. PRESENTING YOUR DATA Data Tables Graphs/Figures
Continuous and discrete variables are graphed differently.
Continuous: line graph, histogram
Discrete : bar chart
(1) Sentence form and (2) table form

15. PRESENTING YOUR DATA Data Tables Graphs/Figures
Continuous and discrete variables are graphed differently.
Continuous: line graph, histogram
Discrete : bar chart
(1) Sentence form and (2) table form

16. SINGLE FACTOR, MORE THAN TWO LEVELS
ANALYZING YOUR DATA
Multiple t-tests are inappropriate for multi-level designs
Increase chances of Type I error 01
One-Factor (or One-Way) Analysis of Variance (ANOVA)
1 IV = One-Way; 2 Ivs = Two-Way ANOVA, Factorial ANOVA for more 02
Once an overall significant effect is found, post-hoc testing is performed.

17. SPECIAL-PURPOSE CONTROL GROUP DESIGNS
Placebo control group
Placebo: inactive substance
Participants think they are being treated, but are not
Placebo effect: When performance of placebo group = experimental group, participant expectations explain the effect of treatment
Wait list control group
To insure equivalent groups in a study of program effectiveness
Wait list group later administered treatment only if shown to be effective (unethical to deny treatment)

18. SPECIAL-PURPOSE CONTROL GROUP DESIGNS
Yoked control group
Each control group subject “yoked” to an experimental group subject.
In experimental designs in which members of an experimental group and a control group are paired, the yoked control group members receive the same stimuli, reinforcements, or punishments as the experimental group members but without the possibility of influencing these effects through their own behavior.

19. SPECIAL PURPOSE CONTROL GROUP DESIGNS
Placebo & Waitlist Control Group Example:
IV  exposure to subliminal recordings
Experimental: weight loss recording
Placebo control: dental pain recording (but told was weight loss tape)
Waitlist control: no tape until wait was over
Double blind procedure used
DV  weight loss
Results  equal amounts of weight loss for all three groups

20. SUMMARY
Depending on your empirical question, you may choose which design to use:
Between-subjects vs. within-subjects
Single factor, two level vs. Single factor, multi-level
Special purpose control group designs
Depending on the type of design, you will choose the appropriate statistical test to test your hypothesis:
Independent-samples vs. paired-samples t-test
ANOVA; if significant, post-hoc tests
Once you have your results, you share them both in writing and in visual form (tables, figures)