Re: Comparing two cross product tables

If you mean you want to compare two 2x2 tables, then maybe try
comparing the log-odds ratio for the two tables. The formula for the
standard error log-odds ratio is very simple; so is the formula for the
standard error for the difference between two log-odds ratios.

Once you have the standard error for the difference of the log-odds
ratio, it should be a straightforward matter to calculate a z
statistic.

You can probably find this test described in several of Alan Agresti's
books on categorical data analysis.

Hope this helps.
--
John Uebersax, PhD

.

Relevant Pages

  • Re: Effect size with no control group?
    ... I mean that it does make sense to me to compare ... with the "standard error" (as it is usually made in t-test of two ... In any case, provided that what I wrote is roughly correct, ...
    (sci.stat.consult)
  • Extending Dunns Test
    ... difference of the mean ranks in the numerator and a standard error in the ... Can one compute z as above but compare the individual p-values ... Kruskal-Wallis is significant at the 0.05 level, ...
    (sci.stat.consult)
  • Extending Dunns Test
    ... difference of the mean ranks in the numerator and a standard error in the ... Can one compute z as above but compare the individual p-values ... Kruskal-Wallis is significant at the 0.05 level, ...
    (sci.stat.math)