The P-Value cannot present a complete measure of association in medical studies considering the association between categorical variables. In such situations, measures are required to reveal the clinical importance of relation along with their statistical significance, as the effect size. This paper aims to introduce the measures of associations for categorical variables and inferences about them in these studies. Principles and method of calculating measures of associations and inference about them including confidence interval and hypothesis testing were presented to assess the relationship between qualitative variables for all types of medical studies taking into account relevant considerations. Additionaly, the method of reporting of findings were introduced in the context of contingency tables. To investigate the relationship between two binary qualitative variables, should be used the Odds Ratio in cross-sectional or case-control studies, the relative risk in cohort studies, and prevalence ratio in cross-sectional studies and risk difference in all type of studies along with their confidence intervals and/or their significance tests considering the independent or related groups of studies. Additionally, for bigger than 2 by 2 tables, the method of calculating of above mentioned measures considering a reference category and other measures such as Phi, Crammers V, contingency and uncertainty coefficients , Lambda, Gamma, Summers D, Kendals tau-b and tau-c would be recommended. In each of these situations, based on research based examples, calculations of tests were performed and their results were presented. To investigate the relationship between a set of risk factors and binary and multi-category qualitative variables, the introduced analyses are recommended considering the situation and purpose of the proposed study.

Keywords: Relationship, Effect Size, Contingency Table, Odds Ratio, Relative Risk, Prevalance Ratio, Risk Difference

Full-Text [PDF 718 kb]   (15718 Downloads)