Example of Chi-Square Analysis using Cross Tabulation and Chi-Square
main topic     interpreting results     session command     see also 

You are interested in determining whether there is an association between gender and activity level for the individuals in your study. Perform a cimage\SQUARED.gif test for association using raw data.

1    Open the worksheet EXH_TABL.MTW. If you have not already done so, set the value order for the variable Activity.

2    Choose Stat > Tables > Cross Tabulation and Chi-Square.

3    Choose Raw data (categorical variables).

4    In Rows, enter Gender. In Columns, enter Activity.

5    Click Chi-Square. Check Chi-square test, Expected cell counts, and Standardized residuals.

6    Click OK in each dialog box.

Session window output

Tabulated Statistics: Gender, Activity

 

 

Rows: Gender   Columns: Activity

 

           Slight  Moderate    A lot  All

 

Female          4        26        5   35

            3.462    23.462    8.077

           0.2894    0.5241  -1.0827

 

Male            5        35       16   56

            5.538    37.538   12.923

          -0.2288   -0.4143   0.8559

 

All             9        61       21   91

 

Cell Contents:      Count

                    Expected count

                    Standardized residual

 

 

Pearson Chi-Square = 2.487, DF = 2, P-Value = 0.288

Likelihood Ratio Chi-Square = 2.613, DF = 2, P-Value = 0.271

 

* NOTE * 1 cells with expected counts less than 5

Interpreting the results

The cells in the table contain the counts, the expected counts, and the standardized residual. There is no evidence of association (p=0.288, 0.271) between Gender and Activity. Because slightly less than 20% (one of six) have expected counts less than five, you may want to interpret the results with caution.