Improving Employee Performance: Analysis of Determinant Factors Using Binary Logistic Regression

The purpose of this study was to analyze the factors that affect employee performance based on the work permit application system in the Information Technology Division of PT. XYZ using the binary logistic regression method. The population of the study was work permits downloaded from the company's work permit system as many as 10,000 sheets, with a sample of 760 work permits selected by simple random sampling. Data processing was carried out statistically through bivariate analysis, multivariate analysis, confounding test, and interaction test. Based on the Nagelkerke R Square test, a value of 0.426 was obtained, which means that the independent variables in the model are able to explain employee performance by 42.6%. The most dominant variable related to employee performance is the work team. Partial tests show that each independent variable such as type of problem, target completion time, and working time have a positive effect on the dependent variable, with a significance level of less than 0.05, thus supporting the hypothesis. However, for the work environment variable, the significance level is greater than 0.05, so the hypothesis is rejected. The results of the simultaneous test in the Omnibus Tests of Model Coefficient table show a significance value (p <0.001), which means that the overall logistic regression model is statistically significant. This means that the hypothesis is accepted, which means that the type of problem, target completion time, work environment, and work team together have a significant influence on the likelihood of employee performance in the Information Technology Division of PT. XYZ Kediri.