Usage of auxiliary variable and neural network in doubly robust estimation

다국어 초록 (Multilingual Abstract)

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 dou-bly robust imputation are approximately unbiased even though both assumed models fail. We also propose a doubly robust estimator of ratio form using population informa-tion of an auxiliary variable. We prove some properties of proposed theory by restricted simulations.

참고문헌 (Reference)

1 조광현, "주변조건부 변수를 이용한 의사결정나무모형 생성에 관한 연구" 한국데이터정보과학회 23 (23): 299-307, 2012

2 박현아, "보조 정보에 의한 이중적 로버스트 대체법" 한국통계학회 18 (18): 47-55, 2011

3 Ekholm, A., "Weighting via response modeling in the finnish household budget survey" 7 : 325-337, 1991

4 Rao, J. N. K., "Variance estimation under two-phase sampling with application to imputation for missing data" 82 : 453-460, 1995

5 Kalton, G., "The treatment of missing survey data" 12 : 1-16, 1986

6 Hastie, T., "The element of statistical learning: Data mining, inference, and prediction, 2nd edition" Springer 2009

7 Little, R. J. A., "Survey nonresponse adjustments for estimates of means" 54 : 139-157, 1986

8 Groves, R., "Survey nonresponse" Wiley 2002

9 Little, R. J. A., "Statistical analysis with missing data" Wiley 2002

10 Iannacchione, V. G., "Sequential weight adjustment for location and cooperation propensity for the 1995 national survey of family growth" 19 : 31-43, 2003

11 Rao, J. N. K., "On variance estimation with imputed survey data" 91 : 499-506, 1996

12 Izenman, A. J., "Modern multivariate statistical techniques: Regression, classiffication, and manifold learning" Springer 2008

13 Rosenbaum, P. R., "Model-based direct adjustment" 82 : 387-394, 1987

14 Kim, J. K., "Imputation using response probability" 34 : 171-182, 2006

15 Cao, W., "Improving efficiency and robustness of the doubly robust estimator for a population mean with incomplete data" 96 : 723-734, 2009

16 Robins, J. M, "Estimation of regression coefficients when some regres-sors are not always observed" 89 : 846-866, 1994

17 Qin, J., "Efficient and doubly robust imputation for covariate-dependent missing responses" 103 : 797-810, 2008

18 Horvitz, D. G., "A generalization of sampling without replacement from a finite universe" 47 : 663-685, 1952

19 Carpenter, J. R., "A comparison of multiple imputation and doubly robust estimation for analyses with missing data" 169 : 571-584, 2006