Two huge categorical datasets produce tiny independence p-values. Which statistic helps compare association strength…
StatisticsLevel: IntermediateBinary and categorical inference
Two huge categorical datasets produce tiny independence p-values. Which statistic helps compare association strength across table sizes?
Hints
- Remove the automatic sample-size inflation.
- Normalize for the table dimensions.
Answer
Cramér's V normalizes chi-square by sample size and the smaller table dimension. Report it alongside uncertainty and substantive context; significance alone is not effect size.
Source and licence: SciPy — contingency tables · BSD-3-Clause · answer: Quantoros editorial