Chi-square test in SPSS, step by step

When to use it

• Two categorical variables (nominal or ordinal categories)
• Independent observations: each respondent counted once
• Expected count of at least 5 in most cells (a common rule: no more than 20% of cells below 5, none below 1)

Steps in SPSS

1. Analyze → Descriptive Statistics → Crosstabs
2. Put one variable in Row(s) and the other in Column(s)
3. Statistics… → tick Chi-square and Phi and Cramér's V
4. Cells… → tick Observed, Expected and Row or Column percentages
5. Click OK

Reading the output

In the Chi-Square Tests table, read the Pearson Chi-Square row: the value, df and Asymptotic Significance (p). Below the table SPSS reports how many cells have expected counts under 5. If that rule is badly broken in a 2×2 table, use Fisher's Exact Test instead.

Then read Cramér's V in the Symmetric Measures table. As a rough guide, values around 0.1 are small, 0.3 medium and 0.5 large, but interpret them in context.

Reporting example (teaching numbers)

“A chi-square test of independence showed a significant association between gender and preferred payment app, χ²(2, N = 180) = 9.42, p = .009, Cramér's V = .23.” Then describe the pattern using the percentages, for example which group preferred which app.

Common mistakes

• Running it on percentages instead of raw counts
• Treating a Likert item with many sparse categories as if expected counts were fine
• Claiming one variable causes the other
• Reporting p without the direction of the association