COMM 88 Lecture Notes - Lecture 12: Random Assignment, Measure R, Internal Validity
11/15/18
●Experimental research
○manipulation/control + random assignment = internal validity
●Types of Experiments
○Design notation
■X: IV manipulation (treatment/induction)
■Y: DV measure
■R: random assignment
●True experiments
○Posttest only control group design
■R X1 Y (group 1)
■R X2 Y (group 2)
●Example:
○R X1 (anti-smoking ad) Y (beliefs about smoking)
○R X2 (no-anti smoking ad) Y (beliefs about smoking)
■If we get difference between group means on Y, the IV caused it
●Variations: more groups, several different treatments
○Example: IV - different types of ad appeals
■X1 Y
■X2 Y
■X3 Y
○Pretest-posttest control group design
■R Y1 X1 Y2 (group 1)
■R Y1 X2 Y2 (group 2)
●Example:
○Get belief about smoking before, than show group 1
anti-smoking ad and group 2 no anti-smoking ad, than test
beliefs about smoking after
■Again, if we get difference between group members (on Y2), the IV caused it.
■Possible problem: differences on Y2, might be the result of interaction of
manipulation with pretest.
○Solomon four-group design
Document Summary
Manipulation/control + random assignment = internal validity. R x2 (no-anti smoking ad) y (beliefs about smoking) If we get difference between group means on y, the iv caused it. Example: iv - different types of ad appeals. Get belief about smoking before, than show group 1 anti-smoking ad and group 2 no anti-smoking ad, than test beliefs about smoking after. Again, if we get difference between group members (on y2), the iv caused it. Possible problem : differences on y2, might be the result of interaction of manipulation with pretest. Solomon four-group design (group 1) (group 2) (group 3) (group 4) Hyp: listening to music (while studying) hinders learning (or improves learning) Purpose: to examine the effects of two or more ivs simultaneously. Each factor/iv has at least two levels (conditions) Study task factor: math problems vs reading comprehension. What if more than two levels of a factor: Factorial design test for two kinds of effects: