Factorial Designs
Factorial Designs
This study tested how alcohol affects video poker play, particularly
among probable pathological gamblers.
Forty-four regular poker players were designated either probable
pathological gamblers or non-pathological gambl

Practice with Factorial Designs
Lets Practice!
For each of these studies, see if you can answer the
following:
a) What is the study type (i.e., between/within/mixed)?
b) What is(are) the IV(s)?
c) What are the levels of each of the IVs?
d) What is the DV

Paired t-tests
Within-Subjects Research Designs
Research Question 1
Does having a window view of a natural setting
speed up healing?
How might we go about testing this?
What if.?
We had access to archival records from a single
hospital and want to us

Factorial ANOVA
Where were at now
Two-Group Designs
One IV with 2 levels
Independent samples t-tests
Multiple-Group Designs
One IV with more than 2 levels
One-way ANOVA
Factorial Designs
More than one IV, each with 2 or more levels
Factorial ANOVA
E

Between-Subjects Two Group Designs:
Wilcoxon Rank Sum Test and Practice
with Independent Samples t-tests
Review: Assumptions of
Independent Samples t-tests
1. Independence
2. Normality
3. Homogeneity of variance
. I said last day that the normality assump

Psyc 312 Review
Exam 4
What is the appropriate analysis?
A psychologist compares a group of home-schooled
children to see if they have stronger religious beliefs
compared to a group of children educated at school.
Independent samples t-test
Or Wilcoxon

Experiments with Two Groups:
Independent Samples t-tests
Lets say you are interested in the
following research question:
How effective are Wilderness Adventure
Therapy Programs for young offenders?
How might we go about testing this?
Jones et al., 2004

16-01-30
Mul$ple Comparisons
What are Mul$ple Comparisons?
Tests suitable for the simultaneous tes3ng of several
hypotheses concerning the equality of three or more
popula3on means
Signicant F only shows that not all

Confidence Limits on the Mean
Point Estimate for Population
Point Estimate
A single value estimate for a population
parameter
Most unbiased point estimate of the population
mean is the sample mean x
Estimate Population
Parameter
Mean:
with Sample
Stati

The One-Sample t-test
Remember our Media Violence Example?
(One-Sample Hypothesis Test)
Does violent content in a video
affect later behaviour?
1. A group of 100 participants saw a violent
video
2. Then free associated to 26 homonyms with
aggressive & no

Statistical Power
What Is Power?
Probability of rejecting a false H0
i.e., probability that youll find difference thats
Ho
Ha
really there
Power = 1 - , where
is the probability of
making a Type II error
Why not ?
is the probability
of making a Type

One-Way Analysis of Variance
(ANOVA)
Multiple Group Designs
Have 1 independent variable with 3 or more
levels
Basically just an extension of 2 group designs
As such, the considerations are essentially the
same
Lets say you are interested in the
followi