제로팽창 음이항 회귀모형에 대한 베이지안 추론 = Bayesian Inference for the Zero In ated Negative Binomial Regression Model

국문 초록 (Abstract)

본 논문에서는 제로팽창 음이항(ZINB) 회귀모형에서 회귀계수에 대한 추론방법으로 마코프체인몬테카를로(MC MC) 기법을 이용한 베이지안 추론방법을 제안하였다. 본 연구에서 고려한 ZINB 회귀모형은 반응변수의 평균뿐만 아니라 제로팽창확률에 대한 회귀모형을 고려한 것으로서 Jang, et al.(2010)의 연구를 확장한 것이다. 아울러 실제사례에 본 연구에서 제안한 베이지안 추론방법을 적용하고 과대산포를 허용하지 않는 제로팽창 포아송(ZIP) 회귀모형과 적합결과를 DIC를 이용하여 비교하였다. 실제 사례분석 결과 ZINB 회귀모형의 DIC가 ZIP모형보다 작게 나타나 ZINB 회귀모형이 ZIP 회귀모형보다 잘 적합되었음을 알 수 있었다.

다국어 초록 (Multilingual Abstract)

In this paper, we propose a Bayesian inference using the Markov Chain Monte Carlo(MCMC) method for the zero inflated negative binomial(ZINB) regression model. The proposed model allows the regression model for zero inflation probability as well as the regression model for the mean of the dependent variable. This extends the work of Jang et al. (2010) to the fully defiend ZINB regression model. In addition, we apply the proposed method to a real data example, and compare the efficiency with the zero inflated Poisson model using the DIC. Since the DIC of the ZINB is smaller than that of the ZIP, the ZINB model shows superior performance over the ZIP model in zero inflated count data with overdispersion.

참고문헌 (Reference)

1 장학진, "영과잉 회귀모형에 대한 베이지안 분석" 한국통계학회 21 (21): 603-613, 2008

2 임아경, "영과잉 포아송 회귀모형에 대한 베이지안 추론: 구강위생 자료에의 적용" 한국통계학회 19 (19): 505-519, 2006

3 Lambert, D, "Zero-inflated poisson regression with an application to defects in manufacturing" 34 : 1-14, 1992

4 Yau, K. K. W., "Zero-inflated negative binomial mixed regression modeling of over-dispersed count data with extra zeros" 45 : 437-452, 2003

5 Seller, C., "Validation of empirical measures of welfare change: A comparison of nonmarket techniques" 61 : 156-175, 1985

6 Cameron, A. C, "Regression Analysis of Count Data" Cambridge University Press 1998

7 Ridout, M. S, "Models for count data with many zeros" 179-192, 1998

8 Gurmu, S, "Excess zeros in count models for recreational trips" 14 : 469-477, 1996

9 Winkelmann, R, "Econometric Analysis of Count Data" Springer 2003

10 Spiegelhalter, D. J., "Bayesian measures of model complexity and fit" 64 : 583-639, 2002

11 Ghosh, S. K., "Bayesian analysis of zero-inflated regression models" 136 : 1360-1375, 2006

12 Rodrigues, J, "Bayesian analysis of zero-inflated distributions, Communications in Statistics" 32 : 281-289, 2003

13 Jang, H. J., "Bayesian analysis for zero-inflated regression models with the power prior: Aapplications to road safety countermeasures" 42 : 540-547, 2010

14 Congdon, P, "Bayesian Models for Categorical Data" John Wiley & Sons 2005

15 Gelman, A., "Bayesian Data Analysis" Chapman & Hall 2004

16 Kass, R. E, "Bayes factors" 90 : 773-795, 1995

17 Ridout, M. S, "A score test for testing a zero-inflated poisson regression model against zero-inflated negative binomial alternatives" 57 : 219-223, 2001

18 Peter, D. H, "A First Course in Bayesian Statistical Methods" Springer 2009