Answers are grounded in this paper and cite their sources.
Summary AN account is given of an experimental determination of certain percentiles of the distribution of the chi-squared statistic for a 3 x 3 contingency table. This suggests that the field of useful application of the chi-squared distribution in testing values of the statistic is wider than it is generally thought to be.
No takes yet. Share an insight, caveat, or question.
J. M. Craddock (1966) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: