Statistics for the Behavioral Sciences by Frederick J. Gravetter, Larry B. Wallnau ISBN 10: 1305504917 ISBN 13: 9781305504912

PREVIEW
Does money in your hands make you feel better? There is
actually some evidence that suggests that handling money
really does reduce pain (Zhou, Vohs, & Baumeister,
2009). In their experiment, a group of college students
was told that they were participating in a manual dexterity
study. The researchers then created two treatment
conditions by manipulating the kind of material that
each participant would be handling. Half of the students
were given a stack of money to count and the other half
got a stack of blank pieces of paper. After the counting
task, the participants were asked to dip their hands into
bowls of very hot water (122°F) and rate how uncomfortable
it was. Participants who had counted money
consistently rated the pain lower than those who had
counted paper.
Although the data show a mean difference between
the two groups, you cannot automatically conclude
that the difference was caused by the materials used
in the counting task. Specifically, the two groups consist
of different people with different backgrounds,
different skills, different IQs, and so on. Because the
two different groups consist of different individuals,
you should expect them to have different scores
and different means. This issue was first presented in
Chapter 1 when we introduced the concept of sampling
error (see Figure 1.2 on page 7). Thus, there are
two possible explanations for the difference between
the two groups.
1. It is possible that there really is a difference
between the two treatment conditions so that
counting money results in less pain than counting
paper.
2. It is possible that there is no difference between
the two treatment conditions and the mean difference
obtained in the experiment is simply the
result of sampling error.
A hypothesis test is necessary to determine which
of the two explanations is most plausible. However, the
hypothesis tests we have examined thus far are intended
to evaluate the data from only one sample. In this study
there are two separate samples.
In this chapter we introduce the independent-measures
t test, which is a solution to the problem. The independentmeasures
t test is a hypothesis test that uses two separate
samples to evaluate the mean difference between two
treatment conditions or between two different populations.
Like the t test introduced in Chapter 9, the independentmeasures
test uses the sample variance to compute an
estimated standard error. This test, however, combines
the variance from the two separate samples to evaluate
the difference between two separate sample means.
10.1 Introduction to the Independent-Measures Design
LEARNING OBJECTIVE
1. Define independent-measures designs and repeated-measures designs.
Until this point, all the inferential statistics we have considered involve using one sample
as the basis for drawing conclusions about one population. Although these single-sample
techniques are used occasionally in real research, most research studies require the comparison
of two (or more) sets of data. For example, a social psychologist may want to compare
men and women in terms of their political attitudes, an educational psychologist may
want to compare two methods for teaching mathematics, or a clinical psychologist may
want to evaluate a therapy technique by comparing depression scores for patients before
therapy with their scores after therapy. When the scores are numerical values, the research
question concerns a mean difference between two sets of data. The research designs that
are used to obtain the two sets of data can be classified in two general categories:
1. The two sets of data could come from two completely separate groups of participants.
For example, the study could involve a sample of men compared with a sample
of women. Or, the study could compare grades for one group of freshmen who are
given laptop computers with grades for a second group who are not given computers.
300