16.4. Higher-Order Contingency Tables
16.4.1. Dyke-Patterson Cancer Knowledge Data
As the number of dimensions of a contingency table increases, there are some complicating factors. One difficulty is the tremendous increase in the number of possible interaction parameters. Another problem is caused by the dramatic increase in the number of cells. Unless the sample size is very large, there may be many observed cell counts equal to zero. There may even be marginal totals equal to zero.
Table 16.10 displays data obtained from a sample of 1729 individuals cross-classified according to five dichotomous variables (Dyke and Patterson 1952). The purpose of the study was to investigate the relationship between cancer knowledge (good, poor) and four ...
Get Categorical Data Analysis Using The SAS® System, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
