Journal of the Korean Data Analysis Society

Korean Data Analysis Society (한국자료분석학회)
권호 표지

Determinants of the Number of Job Experience and Duration to First Job in College

재학 중 경험한 일자리 수와 구직기간 결정요인 분석

  • Cho, Jang Sik (Department of Informational Statistics, Kyungsung University)
  • 조장식 (경성대학교 정보통계학과)
  • Received : 2014.11.03
  • Accepted : 2015.01.27
  • Published : 2015.02.28
⟨ Previous Next ⟩

Abstract

In this paper, we study determinants of the total number of job experience and duration to first job in university using by using graduates occupational mobility survey (GOMS 2009). We set the four models such as Poisson regression model, zero-inflated Poisson model, negative binomial model and zero-inflated negative binomial model. Zero-inflated negative binomial regression model was selected as the optimal model, the main result of the impact on the number of job experience of college are as follows. First, the number of jobs, male experienced in college was small in comparison to female. Second, the number of jobs experience for university is more than the one of college. Third, there is job number one experience in college tend to have increasingly lower GPA (grade point average) up. Also we use Cox's proportional hazard model to analysis duration to first job. The main result of the impact on the duration to first job are as follows. First, male are more likely than female to escape into employment. Second, the greater the number of job experience in college, the higher GPA, as the increase in the number of licenses was higher chance of escape as first job after graduation.

본 연구에서는 대학 재학 중 경험한 일자리 수와 첫 직장의 구직기간과의 관련성을 분석하였다. 이를 위해 먼저 의사결정나무분석을 활용하여 경험한 일자리 수와 관련성 있는 독립변수를 탐색하였다. 계수자료(count data)에 대한 모형으로 포아송 회귀모형(Poisson regression model), 영과잉 포아송 회귀모형, 음이항 회귀모형, 영 과잉 음이항 회귀모형 등 4개의 모형을 설정하여 최적의 모형을 선택하였다. 또한 첫 직장 구직기간에 대한 분석을 위해서 Cox의 비례 해자드 모형(Cox's proportional hazard model)을 이용하였다. 분석결과 재학 중 경험한 일자리 수에 대한 최적 모형으로 영과잉 음이항 회귀모형이 선택이 되었으며, 주요 결과는 다음과 같다. 첫째, 여자에 비해서 남자가 재학 중 경험한 일자리수가 작았으며, 전문대에 비해서 4년제 대학에서 재학 중 경험한 일자리 수가 많은 것을 알 수 있다. 둘째, 연령은 25~30세 사이에서 경험한 일자리 수가 가장 많으며, 평균평점이 높을수록 작음을 알 수 있다. 셋째, 자격증수가 많을수록 경험한 일자리 수가 증가하며, 사립에 비해서 국립이 더 많음을 알 수 있다. 또한 졸업 후 첫 직장의 구직기간에 대한 주요 결과는 남자가 여자에 비해서, 재학 중 경험한 일자리 수가 많을수록, 평균평점이 높을수록, 자격증 수가 증가할수록 졸업 후 첫 직장으로 탈출할 확률이 높은 것으로 나타났다.

Keywords

Acknowledgement

Supported by : 경성대학교

References

  1. Ahn, J. K., Bae, H. J. (2011). The effects of working while in college on the labor market transitions and outcomes, Korean Journal of Sociology of Education, 21(4), 149-180. (in Korean).
  2. Cho, J. S. (2014). A study on determinant factor for number of stop-out, Journal of the Korean Data Analysis Society, 16(1), 201-210. (in Korean).
  3. Choi, J. H., Ko, I. M., Cheon, S. Y. (2011). A zero-inflated model for insurance data, The Korean Journal of Applied Statistics, 24(3), 485-494. (in Korean). https://doi.org/10.5351/KJAS.2011.24.3.485
  4. Cox, D. R. (1983). Some remarks on overdispersion, Biometrika, 70, 269-274. https://doi.org/10.1093/biomet/70.1.269
  5. Dean, C., Lawless, J. F. (1989). Tests for detecting overdispersion in Poisson regression models, Journal of the American Statistical Association, 84(406), 467-472. https://doi.org/10.1080/01621459.1989.10478792
  6. Eckstein, Z., Wolpin, K. I. (1995). Duration to first job and the return to schooling : Estimates from a search-matching model, Review of Economic Studies, 62, 263-286. https://doi.org/10.2307/2297805
  7. Hwang, Y. J., Baek, B. B. (2008). Determinants of employment status of university graduates youth, Journal of Vocational Education and Training, 11, 1-23. (in Korean).
  8. Jeong, J. P., Choi, J. H. (2014). Poisson regression and negative binomial regression model fit for traffic accidents, Journal of the Korean Data Analysis Society, 16(1), 165-172. (in Korean).
  9. Jung, T. Y., Lee, K. Y. (2005). Determinants of job finding among college graduates-with emphasis on the effects of GPA, Korea Business Review, 8(2), 159-184. (in Korean)
  10. Kim, K. M. (2005). A study on the zero-inflated Poisson regression model, Journal of the Korean Data Analysis Society, 7(2), 497-505. (in Korean).
  11. Kim, S. H. (2011). Nonstandard work in college and labor market achievement after graduation, The Journal of Educational Research, 17(2), 5-26. (in Korean).
  12. Kim, K. M., Eum, H. J. (2010). Comparisons of the estimators for the zero-inflated Poisson distribution, Journal of the Korean Data Analysis Society, 12(2), 1113-1124. (in Korean).
  13. Lee, C. Y. (2012). The effect of working while in college on educational outcomes, Journal of Vocational Education and Training, 15(3), 1-25. (in Korean).
  14. Lynch, L. M. (1985). State dependency in youth unemployment: A lost generation?, Journal of Econometrics, 28, 71-84. https://doi.org/10.1016/0304-4076(85)90067-3
  15. Lynch, L. M. (1989). The youth labor market in the eighties: Determinants of re-employment probabilities for young men and women, The Review of Economics and Statistics, 1, 37-45.
  16. Ridout, M., Hinde, J., Demetrio, C. G. B. (2001). A score test for testing a zero-inflated Poisson regression model against zero-inflated negative binomial alternatives, Biometrics, 57, 219-223. https://doi.org/10.1111/j.0006-341X.2001.00219.x
  17. Stinebrickner, R., Stinebrickner, T. R. (2003). Working during school and academic performance, Journal of Labor Economics, 21(2), 449-472. https://doi.org/10.1086/345564
  18. Wenz, M., Yu, W. C. (2010). Term time employment and the academic performance of undergraduates, Journal of Education Finance, 35(4), 358-373. https://doi.org/10.1353/jef.0.0023