Contingency table larger

The hypergeometric distribution can be generalized to a multivariable form, the multivariate hypergeometric distribution, which can be used to extend Fisher s Exact Test to contingency tables larger than 2 by 2 and to multidimensional contingency tables. There is statistical software available to perform these calculations however, due to the complexity of the calculations and the large number of trial tables whose probability of occurrence must be calculated, this extension has received limited use. 

Fisher s exact test should be used to compare two sets of discontinuous, quantal (all or none) data. Small sets of such data can be checked by contingency data tables, such as those of Finney et al. (1963). Larger sets, however, require computation. These include frequency data such as incidences of mortality or certain histopatho-logical findings, and so on. Thus, the data can be expressed as ratios. These data do not fit on a continuous scale of measurement but usually involve numbers of responses classified as either negative or positive that is, contingency table situation (Sokal and Rohlf, 1994). 

The difficulty of interpreting the results from larger contingency tables... 

A similar pattern emerged with contingency chi-square tests (Chapter 16). The simplest 2x2 tables led to clear unambiguous conclusions while results from larger tables were much less easily interpreted. 

---