STATISTICAL SERIES: THE ANALYSIS OF CONTINGENCY TABLES 1 (CHISQUARE TESTS)

Assessing of outcomes and risk factors in the form of qualitative variables is common in the most of medical studies and the research objectives are defined as the relationship between these variables. This paper introduces the concepts and basic and applied statistical tests to examine the relationship between these variables in these studies, including chi-square tests. Principles and method of calculating the statistics and hypothesis testing to assess the relationship between qualitative variables (or difference in proportions between groups), were presented taking into account relevant considerations. The method of reporting findings were introduced in the context of contingency tables, for all types of chi-square tests. To investigate the relationship between two binary or multi-category qualitative variables, Pearson chi-square test (in the case of establishing Cochran conditions), Yates continuity correction for small samples, in the case of not establishing Cochran conditions exact P-Value calculated on the basis of exact tests, trend chi-square test for ordinal qualitative variables and McNemar chi-square test for related samples should be used. In addition for tables larger than 2 × 2, when the overall relationship was significant, post hoc tests with appropriate correction is required. In each of these situations, examples based on research, calculations of tests were performed and their results were presented. To investigate the relationship between a set of risk factors and nominal or ordinal qualitative variables, the introduced analyses are recommended considering the situation and purpose of the proposed study.