응용통계연구 (The Korean Journal of Applied Statistics)

  • 제30권6호
  • /
  • Pages.943-955
  • /
  • 2017
  • /
  • 1225-066X(pISSN)
  • /
  • 2383-5818(eISSN)
한국통계학회 (The Korean Statistical Society)
권호 표지
DOI QR코드

DOI QR Code

19대 대선 전화조사에서 조사방법 효과에 대한 인과연구

Causal study on the effect of survey methods in the 19th presidential election telephone survey

  • 김지현 (숭실대학교 정보통계보험수리학과) ;
  • 정효재 (숭실대학교 정보통계보험수리학과)
  • Kim, Ji-Hyun (Department of Statistics and Actuarial Science, Soongsil University) ;
  • Jung, Hyojae (Department of Statistics and Actuarial Science, Soongsil University)
  • 투고 : 2017.09.28
  • 심사 : 2017.12.07
  • 발행 : 2017.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

전화를 이용한 19대 대선 선거예측조사에서 ARS 조사비율과 무선전화 조사비율을 달리함에 따라 조사결과가 어떻게 달라지는가를 보았다. 조사방법이 조사결과에 미치는 효과를 추정하는 인과연구를 시도하였으며, 이를 위해 변수들 사이의 인과관계를 가정하는 인과 그래프를 그린 다음 모형에 포함시켜야 할 변수와 포함시키면 안 되는 변수를 판단하였다. 조사를 실시한 조사기관은 중첩변수로서 모형에 포함시켜야 하는 변수이며 응답률은 모형에 포함시키면 안 되는 변수임을 설명하였다. ARS 조사비율의 효과는 자료 한계 때문에 추정할 수 없었으며, 무선전화 조사비율이 약 90%를 넘지 않으면 효과에 별 차이가 없으나 전체 조사를 무선전화로만 실시하면 문재인후보지지율이 높아진다.

We investigate and estimate the causal effect of the survey methods in telephone surveys for the 19th presidential election. For this causal study, we draw a causal graph that represents the causal relationship between variables. Then we decide which variables should be included in the model and which variables should not be. We explain why the research agency is a should-be variable and the response rate is a shouldnot-be variable. The effect of ARS can not be estimated due to data limitations. We have found that there is no significant difference in the effect of the proportion of cell phone survey if it is less than about 90 percent. But the support rate for Moon Jae-in gets higher if the survey is performed only by cell phones.

키워드

참고문헌

  1. Friedman, J. H. (1991). Multivariate adaptive regression splines, Annals of Statistics, 19, 1-141. https://doi.org/10.1214/aos/1176347963
  2. Greenland S., Pearl J., and Robins, J. M. (1999). Causal diagrams for epidemiologic research, Epidemiology, 10, 37-48. https://doi.org/10.1097/00001648-199901000-00008
  3. Huh, M. H. and Kim, Y. W. (2008). RDD sample versus directory-based sample for telephone surveys: the case of 2007 presidential election forecasting in Korea, Survey Research, 9, 55-69.
  4. Jang, D. H. and Cho, S. K. (2013). The validity of mobile RDD survey methodology: case study of poll data for 2012 presidential election, Survey Research, 14, 19-47.
  5. Kang, H. C., Han, S. T., Kim, J. Y., Jung, Y. C., and Huh, M. H. (2008). Random digit dialing telephone survey and major findings, Survey Research, 9, 1-22.
  6. Kim, J. Y. and Woo J. Y. (2012). Cell phones and political polls in Korea, Journal of the Korean Association of Party Studies, 11, 225-246.
  7. Kim, Y. and Hwang, D. (2014). Forecasting error and bias of telephone survey for 2014 local election, Survey Research, 15, 1-32.
  8. Lee, K., Lee, H., and Hyun, K. (2012). A study on mixed-mode survey which combine the landline and mobile telephone interviews: the case of special election for the mayor of Seoul, Survey Research, 13, 135-158.
  9. Martin, E. A., Traugott, M. W., and Kennedy, C. (2005). A review and proposal for a new measure of poll accuracy, Public Opinion Quarterly, 69, 342-369. https://doi.org/10.1093/poq/nfi044
  10. Milborrow, S. (2017a). plotmo: Plot a Model's Response and Residuals. R package version 3.3.4. https://CR AN.R-project.org/package=plotmo
  11. Milborrow, S. (2017b). Derived from mda:mars by Trevor Hastie and Rob Tibshirani. Uses Alan Miller's Fortran utilities with Thomas Lumley's leaps wrapper. earth: Multivariate Adaptive Regression Splines. R package version 4.5.1. https://CRAN.R-project.org/package=earth
  12. Pearl, J. (1995). Causal diagrams for empirical research, Biometrika, 82, 669-688. https://doi.org/10.1093/biomet/82.4.669
  13. Pearl, J. (2009). Causality: Models, Reasoning, and Inference, Cambridge University Press, Cambridge.
  14. R Core Team (2016). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/
  15. Thepepomma, S. and Kim, J. (2016). Covariate selection criteria for controlling confounding bias in a causal study, The Korean Journal of Applied Statistics, 29, 849-858. https://doi.org/10.5351/KJAS.2016.29.5.849