DOI QR코드

DOI QR Code

The Analysis of the Number of Donations Based on a Mixture of Poisson Regression Model

포아송 분포의 혼합모형을 이용한 기부 횟수 자료 분석

  • Kim In-Young (Department of Epidemiology and Public Health, School of Medicine, Yale university) ;
  • Park Su-Bum (Korea Health Industry Development Institute) ;
  • Kim Byung-Soo (Department of Applied Statistics, College of Business and Economics, Yonsei University) ;
  • Park Tae-Kyu (Department of Economics, College of Business and Economics, Yonsei University)
  • Published : 2006.03.01

Abstract

The aim of this study is to analyse a survey data on the number of charitable donations using a mixture of two Poisson regression models. The survey was conducted in 2002 by Volunteer 21, an nonprofit organization, based on Koreans, who were older than 20. The mixture of two Poisson distributions is used to model the number of donations based on the empirical distribution of the data. The mixture of two Poisson distributions implies the whole population is subdivided into two groups, one with lesser number of donations and the other with larger number of donations. We fit the mixture of Poisson regression models on the number of donations to identify significant covariates. The expectation-maximization algorithm is employed to estimate the parameters. We computed 95% bootstrap confidence interval based on bias-corrected and accelerated method and used then for selecting significant explanatory variables. As a result, the income variable with four categories and the volunteering variable (1: experience of volunteering, 0: otherwise) turned out to be significant with the positive regression coefficients both in the lesser and the larger donation groups. However, the regression coefficients in the lesser donation group were larger than those in larger donation group.

본 논문에서는 2002년에 (사)볼런티어21에서 실시한 설문조사 자료를 이용하여 2001년에 우리나라 개인들이 기부한 횟수에 영향을 주는 유의한 변수들을 식별하였다. 기부횟수의 경험적 분포로 미루어 모집단은 기부를 적게 하는 집단과 많이 하는 집단으로 구성되며 따라서 모집단 분포를 두개 포아송 분포의 혼합분포로 모형화하였다. 이 모형에 기초하여 기부횟수에 영향을 미치는 변수들을 식별하였다. EM알고리즘을 이용하여 모수를 추정하고 2.5%와 97.5%에 기초한 백분위수 신뢰구간을 보완한 BCa(bias-corrected and accelerated) 신뢰구간을 계산하여 유의한 변수들을 찾았다. 연구결과 혼합 포아송 회귀모형에서는 기부횟수가 적은 집단("작은 군")과 기부횟수가 많은 집단("큰 군") 모두에서 소득과 자원봉사의 경험 유무(1:예, 0:아니오)가 기부횟수에 유의적으로 영향을 주는 변수로 밝혀졌다. 또한 두 변수 각각에서 회귀계수가 양수로 나타나 소득이 많을수록, 혹은 자원봉사의 경험이 있는 사람일수록 기부횟수가 증가하는 것을 알 수 있다. 그러나 소득과 자원봉사 변수의 회귀계수는 "작은 군"이 "큰 군"에 비해 더욱 크게 나타나고 있다. "작은 군"보다 "큰 군"의 사람들에게 기부가 생활화되어 있고, 따라서 소득과 자원봉사의 경험 유무가 기부횟수에 미치는 영향이 상대적으로 적은 것으로 파악된다.

Keywords

References

  1. Akaike, H. (1974). A new look at the statistical model identification. IEEE Transactions on Automatic Control, 19, 716-723 https://doi.org/10.1109/TAC.1974.1100705
  2. Bohning, D., Dietz, E., Schlattmann, P., Mendonca L. and Kirchner, U. (1999). The zero-inflated Poisson model and the decayed, missing and filled teeth index in dental epidemiology. Journal of the Royal Statistical Society A, 162, 194-209
  3. Dempster, A. P., Laird, N. M. and Rubin, D. B. (1997), Maximum likelihood from incomplete data via the EM algorithm (with discussion). Journal of the Royal Statistical Society B, 39, 1-38
  4. Duncan, B. (1999), Modeling charitable contributions of time and money. Journal of Public Economics, 77, 213-242
  5. Efron, B. and Tibshirani, R. J. (1993), An Introduction to the Bootstrap, Chapman & Hall, New York
  6. Hurvich, C. M. and Tsai, C. L. (1989), Regression and Time Series Model Selection in Small Samples. Biometrika, 76, 297-307 https://doi.org/10.1093/biomet/76.2.297
  7. McLachlan, G. and Peel, D. (2000), Finite Mixture Models, Wiley, New York
  8. Park, T. and Park, S. (2004), An economic study on charitable giving of individuals in Korea: some new findings from 2002 survey data, presented at the 6th ISTR conference, Toronto, Canada, 11-14 July 2004
  9. Smith, V. H., Kchoe, M. R. and Creamer, M. E. (1999), The private provision of public goods: Altruism and voluntary giving. Journal of Public Economics, 77, 213-242
  10. van den Broek, Jan. (1995). A score test for zero inflation in a Poisson regression. Biometrics, 51, 738-743 https://doi.org/10.2307/2532959

Cited by

  1. Reanalysis of 2002 Donation Frequency Data: Corrections and Supplements vol.27, pp.5, 2014, https://doi.org/10.5351/KJAS.2014.27.5.743