PERBANDINGAN REGRESI LOGISTIK BINER DAN PROBIT BINER DALAM PEMODELAN TINGKAT PARTISIPASI ANGKATAN KERJA

Abstract

Regression is a data analysis method used to model the relationship between one response variable and one or more predictor variables. In regression modelling, data is often used. In general, the regression model that is often used is simple or multiple regression in modelling where the response variable is quantitative data. The fundamental difference from regression models using quantitative data is the main objective is to estimate the average value of the dependent variable using certain values of the independent variable. Whereas in a regression model with a qualitative dependent variable the main objective is to find the probability of something happening (probability model). One of the development methods of the regression model for data with qualitative response variables is Logistic and Probit regression. The purpose of this study was to compare the best model using binary logistic regression with binary probit regression in the case of Labor Force Participation Rate (TPAK) in Gorontalo City. The research method used is quantitative research methods, with binary logistic regression modelling and binary probit regression. The results showed that the variable that has a significant effect on TPAK Gorontalo City is the open unemployment rate, and the best model between the binary logistic regression model with an AIC value of 1.289 is smaller than the AIC value of the binary Probit regression 1.318, likewise from the R2 value the R2 value for regression is obtained. binary logistic of 12.74%, greater than the R2 value of binary probit regression of 10.70%.