Transcript Matched factorial design

Chapter 9: Experimental Design
One-way design: Only one independent variable is
manipulated. Must have a minimum of two levels
• Simplest is a two group experimental design
• Compare memory for words and nonwords
• Randomized groups: between groups design where
participants are randomly assigned to conditions
• Matched-subjects: participants are matched on a
variable related to the dependent variable and then
randomly assigned to conditions
• Repeated measures: within-subjects design where
each participant completes all conditions
• Posttest design: measure participants on the
dependent variable only after the independent
variable is manipulated.
• Pretest-Posttest design : Participants are first
tested on the dependent variable, then the
independent variable is manipulated, and then
they are again tested in the dependent variable.
• Ensures participants in each condition were
initially equivalent in the dependent variable.
• If there is a pretest score, researchers can see
how much the dependent variable changed.
• More powerful design, making it easier to detect
effects of the independent variable.
• Pretest sensitization: pretest may sensitize
participants to respond to the independent
variable differently than they would if they did not
have the pretest.
• Examining effect of caffeine on memory. First
pretest all participants on the memory test, then
give one group caffeine and the other group a
placebo, and then test their memory again.
• The memory pretest may affect their later
performance on the memory test (may have
practiced, are more familiar with the test).
Factorial Design
• One-way design: test one independent variable
• Factorial design: manipulate two or more
independent variables.
• Factor: refers to each independent variable
• Two-way design: two independent variables
• Three-way design: three independent variables:
2 x 2 design (two way) with 2 levels of each
independent variable
Words
Short
Long
Nonwords
3 x 3 design is a two way design with three levels of
each independent variable
100
0
5
10
200
300
2 x 2 x 3 is a three way design (three independent
variables) with two and three levels each
A1: Words
B1
B2
A2: Nonwords
B1
B2
C1
C1
C2
C2
C3
C3
2 x 3 is a two way design (two independent
variables) but one variable has two levels and
one variable has three levels
A1
A2
A3
No
Cognitive Behavior
Therapy Therapy Therapy
B1
No Drug
B2
Drug
Assignment of participants to conditions:
• Randomized groups factorial design: participants
are randomly assigned to one of the
combinations of the independent variables
• Matched factorial design: match participants
based on their score on a measure related to the
dependent variable.
• If there are 6 cells then choose six highest scores
and randomly assign each to a cell.
• Repeated measure factorial design: all
participants complete all conditions (cells)
• So in a 2 x 2 (4 cells) each participant completes
4 conditions, in a 3 x 3 x 2 (18 cells) each
participant completes all 18 conditions
• Mixed factorial design: has at least one between
and one within subjects variable.
• 2 x 2, one independent variable between
subjects (caffeine no caffeine) and other
independent variable is within subjects (visual
memory test, verbal memory test)
• Randomly assign participants to the between
subjects condition and all participants complete
the within subjects condition.
Main Effect: when there is an effect (or difference)
for one independent variable, collapsing across
the other independent variable.
• 2 (caffeine, no caffeine) x 3 design (short, medium,
long words).
• It is a two way design, so there will be two main
effects (one for caffeine and one for word length)
• If there is a main effect of caffeine, that means that
memory is better in individuals who have caffeine
regardless of the length of words (average across
words).
• If there is a main effect of word length it may be that
memory is better for shorter than longer words,
collapsing across caffeine intake.
Number of Words
Rememberd
Memory for Short, Medium, and Long Words as a
Function on Caffeine Intake
14
12
10
8
6
4
2
0
Caffeine
No Caffeine
Short
Medium
Word Length
Long
Interaction: Occurs when the influence of one
independent variable is different at different levels
of another independent variable.
• 2 (caffeine, no caffeine) x 2 design (short, long
words)
• The effect of caffeine on memory may be different
for short words than for long words.
• Caffeine may only have a positive effect on memory
for short words, but there may be no difference
between caffeine and no caffeine groups for long
words.
• Caffeine interacted with word length
Memory for Words as Function of Word
Length and Caffeine Intake
Number of Words
Remembered
35
30
25
20
caffeine
no caffeine
15
10
5
0
short
long
No interaction, the lines are parallel. The
effect of therapy is the same for the drug
and no drug group.
45
Depression
40
35
30
No Drug
Drug
25
20
15
10
Therapy
No Therapy
A strong interaction, the effect at one level of the
independent variable is opposite of the other level.
35
Accuracy
30
25
20
Verbal
Visual
15
10
5
0
Male
Female
Higher-Order designs:
• Three-way designs: 2 x 2 x 3
• There will be three main effects (A,B,C)
• There will be three two-way interactions: A by B
(ignoring C), A by C (ignoring B), and B by C
(ignoring A).
• There will be one three-way interaction (A by B by
C).
Subject Variable: based on individual personal
characteristics that you can not manipulate but
you can measure (age, IQ, gender).
Expericorr (mixed) design: has at least one
independent variable manipulated by the
researcher and at least one subject variable
(gender) measured but not manipulated.
• Allows researchers to examine effects of a subject
variable
• Help to understand how personal characteristics
relate to behavior (age, gender)
• Dividing participants into groups based on a
subject variable makes the participants in each
group more homogeneous
Classifying participants into groups:
• Median-split procedure: divide participants
into two groups based on the median score
(half of the participants above and half below
this score).
• Extreme groups procedure: divide
participants into two groups based on very
high and low scores on a variable of interest.
• These procedures can throw away valuable
information.
• With median split the participants may not
truly be high or low, they may just be high or
low in the sample but not in the population.
Cautions with mixed designs:
• The subject variable it not manipulated so this
simply provide correlational findings, but not
causality.