$\require{mediawiki-texvc}$

연합인증

연합인증 가입 기관의 연구자들은 소속기관의 인증정보(ID와 암호)를 이용해 다른 대학, 연구기관, 서비스 공급자의 다양한 온라인 자원과 연구 데이터를 이용할 수 있습니다.

이는 여행자가 자국에서 발행 받은 여권으로 세계 각국을 자유롭게 여행할 수 있는 것과 같습니다.

연합인증으로 이용이 가능한 서비스는 NTIS, DataON, Edison, Kafe, Webinar 등이 있습니다.

한번의 인증절차만으로 연합인증 가입 서비스에 추가 로그인 없이 이용이 가능합니다.

다만, 연합인증을 위해서는 최초 1회만 인증 절차가 필요합니다. (회원이 아닐 경우 회원 가입이 필요합니다.)

연합인증 절차는 다음과 같습니다.

최초이용시에는
ScienceON에 로그인 → 연합인증 서비스 접속 → 로그인 (본인 확인 또는 회원가입) → 서비스 이용

그 이후에는
ScienceON 로그인 → 연합인증 서비스 접속 → 서비스 이용

연합인증을 활용하시면 KISTI가 제공하는 다양한 서비스를 편리하게 이용하실 수 있습니다.

Usage of auxiliary variable and neural network in doubly robust estimation 원문보기

Journal of the Korean Data & Information Science Society = 한국데이터정보과학회지, v.24 no.3, 2013년, pp.659 - 667  

Park, Hyeonah (Department of Statistics, Seoul National University) ,  Park, Wonjun (Department of Statistics, Seoul National University)

Abstract AI-Helper 아이콘AI-Helper

If the regression model or the propensity model is correct, the unbiasedness of the estimator using doubly robust imputation can be guaranteed. Using a neural network instead of a logistic regression model for the propensity model, the estimators using doubly robust imputation are approximately unbi...

주제어

AI 본문요약
AI-Helper 아이콘 AI-Helper

* AI 자동 식별 결과로 적합하지 않은 문장이 있을 수 있으니, 이용에 유의하시기 바랍니다.

제안 방법

  • Doubly robust estimators using estimated propensity function by neural network are asymptotically unbiased but doubly robust estimators using estimated propensity function by logistic model are biased as long as the regression model is incorrect and nonlinear response model for propensity model is used. Simulation results were suggested to test our theory under some restricted population model and propensity model in this thesis. An auxiliary variable with population information is only used for doubly robust estimators in this paper.

이론/모형

  • If the remarks the regression model is incorrect and the propensity model is correct, the estimator using regression imputation is biased but the estimators using doubly robust imputation are unbiased. Doubly robust estimators using estimated propensity function by neural network are asymptotically unbiased but doubly robust estimators using estimated propensity function by logistic model are biased as long as the regression model is incorrect and nonlinear response model for propensity model is used. Simulation results were suggested to test our theory under some restricted population model and propensity model in this thesis.
  • We use the maximum likelihood method to estimate the logistic model and compute the values of α0 and α1 iteratively using the Newton-Raphson method.
본문요약 정보가 도움이 되었나요?

참고문헌 (19)

  1. Carpenter, J. R. and Kenward, M. G. (2006). A comparison of multiple imputation and doubly robust estimation for analyses with missing data. Journal of the Royal Statistical Society A, 169, 571-584. 

  2. Cao, W., Tsiatis, A. A. and Davidian, M. (2009). Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data. Biometrika, 96, 723-734. 

  3. Cho, K. H. and Park, H. C. (2012). A study on decision tree creation using marginally conditional variables. Journal of the Korean Data & Information Science Society, 23, 299-307. 

  4. Ekholm, A. and Laaksonen, S. (1991). Weighting via response modeling in the finnish household budget survey. Journal of Official statistics, 7, 325-337. 

  5. Groves, R., Dillman, D., Eltinge, J. and Little, R. J. A. (2002). Survey nonresponse, Wiley, New York. 

  6. Hastie, T., Tibshirani, R. and Friedman, J. (2009). The element of statistical learning: Data mining, inference, and prediction, 2nd edition, Springer, New York. 

  7. Horvitz, D. G. and Thompson, D. J. (1952). A generalization of sampling without replacement from a finite universe. Journal of the American Statistical Society, 47, 663-685. 

  8. Iannacchione, V. G. (2003). Sequential weight adjustment for location and cooperation propensity for the 1995 national survey of family growth. Journal of Official statistics, 19, 31-43. 

  9. Izenman, A. J. (2008). Modern multivariate statistical techniques: Regression, classification, and manifold learning, Springer, New York. 

  10. Kalton, G. and Kasprzyk, D. (1986). The treatment of missing survey data. Survey Methodology, 12, 1-16. 

  11. Kim, J. K. and Park, H. (2006). Imputation using response probability. The Canadian Journal of Statistics, 34, 171-182. 

  12. Little, R. J. A. (1986). Survey nonresponse adjustments for estimates of means. International Statistical Review, 54, 139-157. 

  13. Little, R. J. A. and Rubin, D. B. (2002). Statistical analysis with missing data, Wiley, New York. 

  14. Park, H., Jeon, J. and Na, S. (2011). Doubly robust imputation using auxiliary information. Communications of the Korean Statistical society, 18, 47-55. 

  15. Qin, J., Shao, J. and Zhang, B. (2008). Efficient and doubly robust imputation for covariate-dependent missing responses. Journal of the American Statistical Association, 103, 797-810. 

  16. Rao, J. N. K. and Sitter, R. R. (1995). Variance estimation under two-phase sampling with application to imputation for missing data. Biometrika, 82, 453-460. 

  17. Rao, J. N. K. (1996). On variance estimation with imputed survey data. Journal of the American Statistical Association, 91, 499-506. 

  18. Robins, J. M, Rotnitzky, A. and Zhao, L. P. (1994). Estimation of regression coefficients when some regressors are not always observed. Journal of the American Statistical Association, 89, 846-866. 

  19. Rosenbaum, P. R. (1987). Model-based direct adjustment. Journal of the American Statistical Association, 82, 387-394. 

저자의 다른 논문 :

LOADING...

관련 콘텐츠

오픈액세스(OA) 유형

GOLD

오픈액세스 학술지에 출판된 논문

저작권 관리 안내
섹션별 컨텐츠 바로가기

AI-Helper ※ AI-Helper는 오픈소스 모델을 사용합니다.

AI-Helper 아이콘
AI-Helper
안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

선택된 텍스트

맨위로