College graduate’s job satisfaction analysis using quantile regression model†
Jangsik Cho1 · Jeonghwan Ko2
1Department of Big Data and Applied Statistics, Kyungsung University
2Department of Data Science, Andong National University
2Department of Data Science, Andong National University
Correspondence to: † This work was supported by a Research Grant of Andong Nation University.
1 Professor, Department of Big Data and Applied Statistics, Kyungsung University, Busan 48434, Korea.
2 Corresponding author: Professor, Department of Data Science, Andong National University, Andong 36729, Korea. E-mail : jhko@andong.ac.kr.
1 Professor, Department of Big Data and Applied Statistics, Kyungsung University, Busan 48434, Korea.
2 Corresponding author: Professor, Department of Data Science, Andong National University, Andong 36729, Korea. E-mail : jhko@andong.ac.kr.
Received September 23, 2024; Revised October 27, 2024; Accepted October 30, 2024.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
- Abstract
- In this paper, the determinants for college graduate’s job satisfaction is analysed using 2020 GOMS data. In general, regression models using the ordinary least squares method (OLS) not only provide average trend information on job satisfaction for independent variables, but also must satisfy conditions such as normality, independence, and homoscedasticity. In particular, there is a possibility that the determinants of the influence on job satisfaction may differ depending on the level of job satisfaction. In order to overcome these problems, we used a quantile regression model to estimate the rate of change at all levels of the distribution of the dependent variable. The main results are summarized as follows. First, it was found that the mood regression model was more valid than the OLS regression model. Second, the regression coefficients by quantile were found to be significant for most independent variables, including gender, average grade, major, and initial salary. Third, the results of the quantile regression model were different from those of the regression model using the least squares method. Also it was found that the size of the regression coefficient, the pattern and sign of the increase and decrease, and the degree of significance could change, especially at extreme values of the quantile.
- Keywords : Heteroscedasticity, job satisfaction, ordinary least squares method, quantile regression
Full Text(PDF) Free
