To be a true contingency table, each value must represent numbers of subjects (or experimental units). Is your table really a contingency table? Paired data should not be analyzed by chi-square or Fisher's test. These data should be analyzed by special methods such as McNemar's test. One subject in each pair receives one treatment while the other subject gets the other treatment. In some experiments, subjects are matched for age and other variables. Neither of these tests is offered by Prism. To analyze this kind of data, use the Mantel-Haenszel test or logistic regression. You do not have 100 independent observations. Any difference between hospitals, or the patient groups they serve, would affect half the subjects but not the other half. These subjects are not independent if the table combines results from 50 subjects in one hospital with 50 subjects from another hospital. For example, suppose that the rows of the table represent two different kinds of preoperative antibiotics and the columns denote whether or not there was a postoperative infection. You must think about the experimental design. That means that any factor that affects the outcome of one subject only affects that one subject. The results of a chi-square or Fisher's test only make sense if each subject (or experimental unit) is independent of the rest. Read elsewhere to learn about relative risks & odds ratios, sensitivity & specificity, and interpreting P values. Contingency tables summarize results where you compared two or more groups and the outcome is a categorical variable (such as disease vs.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |