Psych 100A Final Review Session Notes
Dawn Chen
December 8, 2009
How to Decide What Type of Hypothesis Test to Use
Test
When to use this test
Onesample
z
test
You want to compare the scores in your sample to the population
average
(
),
μ
and
σ
is known
Onesample
t
test
You want to compare the scores in your sample to the population
average (
),
μ
and
σ
is unknown
Independent samples
z
test
You want to compare the scores of one group to the scores of a separate
group, and
1
2
,
σ
σ
are known
Independent samples
t
test
You want to compare the scores of one group to the scores of a separate
group, and
1
2
,
σ
σ
are unknown but can be assumed to be equal
Dependent samples
t

test
You want to compare two sets of scores for the same group or you want
to compare the scores of two related groups
Twotailed (non
directional) test
You want to see if there is a difference between the scores of the two
groups
Onetailed
(directional) test
You want to see if the scores of one group are higher than (or lower
than) the scores of the other group
Onefactor between
subjects ANOVA
You want to compare the scores of three or more separate groups, each
of which had or received one level of one independent variable (IV)
Twofactor between
subjects ANOVA
There are two IVs, and each combination of the levels of one IV with
the levels of the other IV is given to a separate group of subjects
Onefactor within
subjects ANOVA
There is one IV with three or more levels, and each level of the IV is
given to the same group of subjects
Chisquare test for
goodnessoffit
There is one nominal dependent variable (DV), and you want to see
whether the actual number of observations in each category of the DV
matches the expected number of observations for that category
Chisquare test of
independence
There are two nominal variables, and you want to see whether they are
related (if certain values of one variable tend to occur with certain
values of the other variable)
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
For the hypothesis tests that we learned in this class, you can follow the flow chart below
to decide which one to use.
Each rectangle represents a question you can ask and each oval
represents a test you can use.
To decide whether it’s a betweensubjects or withinsubjects design, we look at the
wording of the problem.
It there is random assignment (subjects are randomly assigned to one of
two or more groups), then it’s a betweensubjects design.
A betweensubjects design is one in
which each subject gets one treatment
or
a different treatment (or a third one, and so on), or each
subject possesses one characteristic or a different characteristic (e.g. gender, a subject can only
be male or female).
A withinsubjects design is one in which each subject gets one treatment
and
another treatment (and a third one, and so on).
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '10
 Chen
 Statistics, Least Squares, Normal Distribution, Statistical tests, ice cream, Chisquare distribution

Click to edit the document details