Chi-square and G–tests of goodness-of-fit or independence give inaccurate results when the expected numbers are small. When the sample sizes are too small, you should use exact tests instead of the ch...Chi-square and G–tests of goodness-of-fit or independence give inaccurate results when the expected numbers are small. When the sample sizes are too small, you should use exact tests instead of the chi-square test or G–test.
