A Study of Factors That Influencing the External Audit Process Using the Cohen's Kappa Regression Model (Survey of a Sample of Employees in the Iraqi Ministry of Oil)

Abstract

Nonparametric measures of agreement and association are essential statistical tools for assessing the relationship between two variables, especially with small sample sizes or when there is no prior knowledge of the population's distribution. The Cohen-Kappa statistic is considered one of the most important nonparametric tests for measuring agreement and association between two variables. This statistic approximates the z-distribution, which is then used to test hypotheses about Cohen-Kappa. Diagnosing the relationships among multiple Cohen-Kappa coefficients is crucial for understanding how variables are connected under the influence of a metric covariate. Therefore, researchers have used regression techniques to analyze relationships among several variables using Cohen-Kappa coefficients. In this study, the Cohen-Kappa regression method was applied to identify key factors affecting internal auditing processes, using data from internal auditors working within the organizational units of the Iraqi Ministry of Oil. The Kappa regression model was analyzed, and its parameters were estimated using both the Maximum Likelihood Estimation (MLE) method and Ridge Regression. The findings indicate the superiority of the Ridge Regression approach in analyzing the factors affecting internal auditing quality.