SPSS Crosstabulation
The next function of SPSS for Windows that we are going to show you is how to
conduct a ChiSquared test. For this purpose we have chosen a contingency table
between gender and shopping duty.
Before we ask the computer to perform any calculation for us, we should be clear
about the nature of our test. The objective of Chisquared test of independence is to
look into the associative relationship between two nominal/ordinal variables. Nominal
variables are variables like sex or occupation that partitions the respondents into a
number of categories/groups. For instance, the variable sex categorizes respondents
into the male group and female group. If these groups are represented by a code
number in the computer, it can be 1 for male and 2 for female. Alternatively, it is
equally valid to code male as 2 and female as 1. As a result, the coding is arbitrarily.
The consequence of this is the computation of the mean and variance for the variable
becomes meaningless, and in fact all parametric statistical methods cannot be utilized
for these variables. To look at the relationship between nominal variables, we need to
use nonparametric techniques like the chisquared test. Ordinal data are often
assumed to have interval data properties, so common parametric methods are more
often used for these data.
The null hypothesis for the chisquared test states that gender and shopping duty is
independent, and the alternative hypothesis says that the two variables are dependent.
To run the chisquared test, simply click on the pull down menu
Analyze
, select
Descriptive Statistics
and choose
Crosstabs
to open up the following dialogue
box.
Select Gender from the variable list and click on the right arrow button to put it
into the Row variable box. For the column variable, select Shopping Duty, the
variable representing and put it into the Column variable box by clicking on the
corresponding right arrow button.
1
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentNow that you have specified the row variable and the column variable, click
Cells
to
pop up another dialogue box. In this dialog box, select
Expected
under
Counts
to ask
SPSS to compute the expected frequency of each cell. Since the dependent variable is
This is the end of the preview.
Sign up
to
access the rest of the document.
 Fall '08
 Alan
 Marketing, Pearson's chisquare test, Count Expected Count, shopping duty

Click to edit the document details