Robust estimation and inference for general varying coefficient models with missing observations

TEST - 2020
Francesco Bravo1
1Department of Economics, University of York, York, UK

Tóm tắt

AbstractThis paper considers estimation and inference for a class of varying coefficient models in which some of the responses and some of the covariates are missing at random and outliers are present. The paper proposes two general estimators—and a computationally attractive and asymptotically equivalent one-step version of them—that combine inverse probability weighting and robust local linear estimation. The paper also considers inference for the unknown infinite-dimensional parameter and proposes two Wald statistics that are shown to have power under a sequence of local Pitman drifts and are consistent as the drifts diverge. The results of the paper are illustrated with three examples: robust local generalized estimating equations, robust local quasi-likelihood and robust local nonlinear least squares estimation. A simulation study shows that the proposed estimators and test statistics have competitive finite sample properties, whereas two empirical examples illustrate the applicability of the proposed estimation and testing methods.

Từ khóa


Tài liệu tham khảo

Bianco A, Spano P (2019) Robust inference in nonlinear regression models. Test 28:369–398

Bianco A, Yohai V (1996) Robust estimation in the logistic regression model. In: Robust statistics, data analysis and computer intensive methods, Lecture Notes in Statistics 109, Springer, New York

Bianco A, Boente G, Martinez E (2006) Robust tests in semiparametric partly linear models. Scand J Stat 33:435–450

Bianco A, Boente G, Sombielle S (2011) Robust estimation for nonparametric generalized regression. Stat Probab Lett 81:1986–1994

Bianco A, Boente G, Gonzalez-Manteiga W, Perez A (2019) Plug-in marginal estimation under general regression model with missing responses and covariates. Test 28:106–146

Boente G, He X, Zhou J (2006) Robust estimates in generalized partially linear models. Ann Stat 34:2856–2878

Boente G, Gonzalez-Manteiga W, Perez-Gonzalez A (2009) Robust nonparametric estimation with missing data. J Stat Plan Inference 139:571–592

Bravo F (2015) Semiparametric estimation with missing covariates. J Multivar Anal 139:329–346

Bravo F, Jacho-Chavez D (2016) Semiparametric quasi-likelihood estimation with missing data. Commun Stat Theory Methods 46:1345–1369

Cai Z, Fan J, Li R (2000) Efficient estimation and inference for varying-coefficient models. J Am Stat Assoc 95:888–902

Cantoni E, Ronchetti E (2001) Robust inference for generalized linear models. J Am Stat Assoc 96:1022–1030

Carroll R, Ruppert D (1988) Transformation and weighting in regression. Chapman and Hall, London

Chen J, Fan J, Li K, Zhou H (2006) Local quasi-likelihood estimation with data missing at random. Statistica Sinica 16:1071–1100

Cheng P (1994) Nonparametric estimation of mean functionals with data missing at random. J Am Stat Assoc 89:81–87

Eubank R, Huang C, Munoz Maldonado Y, Wang N, Wang S, Buchanan R (2004) Smoothing spline estimation in varying-coefficient models. J R Stat Soc B 66:653–667

Fan J, Gijbels I (1996) Local polynomial modeling and its applications. Chapman and Hall, London

Fan J, Hu TC, Truong Y (1994) Robust non-parametric function estimation. Scand J Stat 21:433–446

Fan J, Heckman N, Wand M (1995) Local polynomial kernel regression for generalized linear models and quasilikelihood functions. J Am Stat Assoc 90:141–150

Fan J, Farmer M, Gijbels I (1998) Local maximum likelihood estimation and inference. J R Stat Soc B 60:591–608

Hahn J (1998) On the role of the propensity score in efficient semiparametric estimation of average treatment effects. Econometrica 66:315–331

Hastie T, Tibshirani R (1993) Varying-coefficient models (with discussion). J R Stat Soc 55:757–796

He X, Fung W, Zhu Z (2005) Robust estimation in generalized partial linear models for clustered data. J Am Stat Assoc 100:1176–1184

Horvitz D, Thompson D (1952) A generalization of sampling without replacement from a finite universe. J Am Stat Assoc 47:663–685

Hu T, Cui H (2010) Robust estimates in generalised varying coefficient partially linear models. J Nonparametric Stat 22:737–754

Huang J, Wu C, Zhou L (2002) Varying-coefficient models and basis function approximations for the analysis of repeated measurements. Biometrika 89:111–128

Ibrahim J, Molenberghs G (2009) Missing data methods in longitudinal studies: a review. Test 18:1–43

Kurum E, Li R, Senturk D, Wang Y (2013) Nonlinear varying coefficient models with application to a photosynthesis study. J Agric Biol Environ Stat 19:57–81

Lia L, Shen X, Li X, Robins J (2013) On weighting approaches for missing data. Stat Methods Med Res 22:14–30

Liang H (2008) Generalized partially linear models with missing covariates. J Multivar Anal 99:880–895

Liang K, Zeger S (1986) Longitudinal data analysis using generalised linear models. Biometrika 73:13–22

Liang H, Wang S, Robins J, Carroll R (2004) Estimation in partially linear models with missing covariates. J Am Stat Assoc 99:357–367

Parzen M (2009) A random effects model for simulating clustered binary data. Technical Report, Harvard University

Robins J, Gill R (1997) Non-response models for the analysis of non-monotone ignorable missing data. Stat Med 16:39–56

Robins J, Rotnitzky A (1995) Analysis of semiparametric models for repeated outcomes and missing data. J Am Stat Assoc 90:106–121

Robins J, Rotnitzky A, Zhao L (1994) Estimation of regression coefficients when some of the regressors are not always observed. J Am Stat Stat Assoc 89:846–866

Ruppert D, Wand P (1994) Multivariate locally weighted least squares regression. Ann Stat 22:1346–1370

Scharfstein D, Rotnitzky A, Robins J (1999) Adjusting for ignorable drop-out using semiparametric nonresponse models. J Am Stat Assoc 94:1096–1120

Verhasselt A (2014) Generalized varying coefficient models: a smooth variable selection technique. Statistica Sinica 24:147–171

Wedderburn R (1974) Quasi-likelihood functions, generalized linear models and the gauss-newton method. Biometrika 61:439–447

Thông tin
Thông tin xuất bản

TEST

Thông tin tác giả