This preview shows pages 1–2. Sign up to view the full content.
Psych 100A Week 9 Discussion Notes Part 2:
The OneFactor BetweenSubjects Analysis of Variance
November 27, 2009
Dawn Chen
Remember that
t
tests are used when we have only two groups of observations.
When
there are more groups, we usually use a family of tests called analysis of variance
(ANOVA).
The onefactor (or oneway) betweensubjects ANOVA is a statistical hypothesis testing
procedure that is used when we have one independent variable with three or more levels, each of
which is either administered to (if the independent variable is a treatment) or possessed by (if the
independent variable is a characteristic of the subject, such as ethnicity) a separate, independent
group of subjects.
For example, let’s consider the following experiment:
A social psychologist was
interested in the effect of crowds on response to emergency situations.
To evaluate this effect,
each of 12 subjects was randomly assigned to 1 of 3 conditions: alone, 2 other people in the
room, or 4 other people in the room.
Subjects saw smoke coming from the next room.
The
researcher measured how many minutes it took subjects to react and do something.
The results
are shown in the following table:
Alone
2 other people
4 other people
8
8
10
8
6
8
9
15
24
11
19
18
Mean
9
12
15
Here, the independent variable is the number of other people in the room, with three
levels: 0, 2, and 4.
Since the independent variable has three levels, each of which is given to a
separate, independent group of subjects, the onefactor betweensubjects ANOVA is the
appropriate test for this experiment.
In this example and in general, we are still interested in whether the mean scores on the
dependent variable among the different groups are significantly different.
In this example, we
are interested in whether the mean reaction times of the different groups are significantly
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview. Sign up
to
access the rest of the document.
 Spring '10
 Chen
 Statistics, Variance

Click to edit the document details