STATISTICAL SERIES: THE ANALYSIS OF CONTINGNCY TABLES 3 (MEASURES OF EFFECT AND AGREEMENT)

In medical studies، measures are required to reveal the effect of exposures and interventions and also the precision of measurements. This paper aimed to introduce the measures of effect and agreement and inferences about them in these studies. Principles and method of calculating measures of effect and agreement and inference about them were presented for all types of medical studies taking into account the relevant considerations. To assess the effect of risk factors on outcomes in case-control and cohort studies، and to determine the relevant effect، the attributable risk and fraction in the exposed group and population were used along with their confidence intervals. Also the relative risk reduction، absolute risk reduction and number needed to treat were applied as the measures of effect of intervention in the interventional studies especially in trails. The sensitivity، specificity and related measures along with their confidence intervals were computed for diagnostic accuracy and screening studies. In addition it is needed to evaluate the precision of measurements using standard error of measurements، ICC، Altman and Bland’s limits of agreement and Lin’s concordance correlation coefficient for quantitative variables and using kappa and weighted kappa for nominal and ordinal variables. In each of these situations the results of research based examples were presented along with the methods of their calculations. To assess the measures of effect and agreement، the mentioned analyses are recommended considering the situation and purpose of the study.