- Open your data file in SPSS.
- Click on “Analyze” in the top menu, then select “Descriptive Statistics” > “Crosstabs”
- In the Crosstabs dialog box:
- Move one categorical variable into the “Row(s)” box.
- Move the other categorical variable into the “Column(s)” box.
- Click on the “Statistics” button and check the box for “Chi-square”
- Click on the “Cells” button and ensure “Observed” is checked under “Counts”
- Click “Continue” and then “OK” to run the analysis.
Interpreting the Results
- Look for the “Chi-Square Tests” table in the output
- Find the “Pearson Chi-Square” row and check the significance value (p-value) in the “Asymptotic Significance (2-sided)” column
- If the p-value is less than your chosen significance level (typically 0.05), you can reject the null hypothesis and conclude there is a significant association between the variables
Main Weakness of Chi-square Test
The main weakness of the Chi-square test is its sensitivity to sample size[3]. Specifically:
- Assumption violation: The test assumes that the expected frequency in each cell should be 5 or more in at least 80% of the cells, and no cell should have an expected frequency of less than 1
- Sample size issues:
- With small sample sizes, the test may not be valid as it’s more likely to violate the above assumption.
- With very large sample sizes, even small, practically insignificant differences can appear statistically significant.
To address this weakness, always check the “Expected Count” in your output to ensure the assumption is met. If not, consider combining categories or using alternative tests for small samples, such as Fisher’s Exact Test for 2×2 tables