Chi-square test of independence
Test whether two categorical variables are associated.
When to use it
Use this when both variables are categories and you want to know whether the pattern of counts could have come from independence. For example: does passing a quiz depend on teaching method?
Assumptions
Each row is one case. Expected counts should be at least 5 in most cells. Tensr stores low_expected_cells, the number of cells whose expected count is under 5. When that number is high, use Fisher’s exact test on a 2×2 table.
Running it in Tensr
Options
Prop
Type
Reading the output
Gender and writing hand in the class. The two were drawn independently.
| gender | Left | Right |
|---|---|---|
| Man | 5 | 42 |
| Woman | 12 | 37 |
Chi-square test of independence between gender and hand, 96 complete rows. The primary result is not significant (p = .131). This is not large enough to treat the comparison this page is about as a reliable association. The result is non-significant: the data are still compatible with no effect. Metrics: χ² = 2.28; df = 1; p-value = .131.
Reporting (APA 7)
Chi-square test of independence between gender and hand, 96 complete rows. This result is not significant (p = .131). Report the estimate with that p, and do not describe the pattern as a reliable effect.
Coming from SPSS
Analyze → Descriptive Statistics → Crosstabs, with Chi-square, Phi, and Cramér’s V. SPSS prints expected counts in the crosstab. Tensr stores them on expected_counts and counts how many fall under 5.