Statistical inference for partially linear regression models with measurement errors

Abstract

In this paper, the authors investigate three aspects of statistical inference for the partially linear regression models where some covariates are measured with errors. Firstly, a bandwidth selection procedure is proposed, which is a combination of the difference-based technique and GCV method. Secondly, a goodness-of-fit test procedure is proposed, which is an extension of the generalized likelihood technique. Thirdly, a variable selection procedure for the parametric part is provided based on the nonconcave penalization and corrected profile least squares. Same as “Variable selection via nonconcave penalized likelihood and its oracle properties” (J. Amer. Statist. Assoc., 96, 2001, 1348–1360), it is shown that the resulting estimator has an oracle property with a proper choice of regularization parameters and penalty function. Simulation studies are conducted to illustrate the finite sample performances of the proposed procedures.

Keywords

Partially linear model / Measurement error / Bandwidth selection / Goodness-of-fit test / Oracle property

References

[1] Antoniadis A., Fan J.. Regularization of wavelet approximations. J. Amer. Statist. Assoc., 2001, 96: 939-967 with discussion and a rejoinder by the authors)

[2] Bickel P. J., Kwon J.. Inference for semiparametric models: some questions and an answer. Statist. Sinica, 2001, 11: 863-960 (with comments and a rejoinder by the authors)

[3] Breiman L.. Better subset regression using the nonnegative garrote. Technometrics, 1995, 37: 373-384

[4] Cai J., Fan J., Li R., Zhou H.. Model selection for multivariate failure time data. Biometrika, 2005, 92: 303-316

[5] Carroll R. J., Ruppert D., Stefanski L. A.. Measurement Error in Nonlinear Models, 1995, London: Chapman and Hall

[6] Chen H.. Convergence rates for parametric components in a partly linear model. Ann. Statist., 1988, 16: 136-146

[7] Chen H., Shiau J. H.. A two-stage spline smoothing method for partially linear models. J. Statist. Plann. Infer., 1991, 27: 187-202

[8] Chen H., Shiau J. H.. Data-driven efficient estimators for a partially linear model. Ann. Statist., 1994, 22: 211-237

[9] Cheng C. L., Tsai C. L.. The invariance of some score tests in the linear model with classical measurement error. J. Amer. Statist. Assoc., 2004, 99: 805-809

[10] Cui H., Li R.. On parameter estimation for semi-linear errors-in-variables models. J. Multivar. Anal., 1998, 64: 1-24

[11] Donald G., Newey K.. Series estimation of semilinear models. J. Multivar. Anal., 1994, 50: 30-40

[12] Engle R. F., Granger C. W. J., Rice J., Weiss A.. Semiparametric estimates of the relation between weather and electricity sales. J. Amer. Statist. Assoc., 1986, 81: 310-320

[13] Eubank R., Hart J. D., Speckman P.. Trigonometric series regression estimators with an application to partially linear models. J. Multivar. Anal., 1990, 32: 70-83

[14] Fan J., Gijbels I.. Local Polynomial Modeling and Its Applications, 1996, London: Chapman and Hall

[15] Fan J., Li R.. Variable selection via nonconcave penalized likelihood and its oracle properties. J. Amer. Statist. Assoc., 2001, 96: 1348-1360

[16] Fan J., Li R.. Variable selection for Cox’s proportional Hazards model and frailty model. Ann. Statist., 2002, 30: 74-99

[17] Fan J., Li R.. New estimation and model selection procedures for semiparametric modeling in longitudinal data analysis. J. Amer. Statist. Assoc., 2004, 99: 710-723

[18] Fan J., Peng H.. Non-concave penalized likelihood with diverging number of parameters. Ann. Statist., 2004, 32: 928-961

[19] Fan J., Zhang C., Zhang J.. Generalized likelihood ratio statistics and Wilks phenomenon. Ann. Statist., 2001, 29: 153-193

[20] Frank I. E., Friedman J. H.. A statistical view of some chemometrics regression tools. Technometrics, 1993, 35: 109-148 with discussion)

[21] Hamilton S. A., Truong Y. K.. Local linear estimation in partly linear models. J. Multivar. Anal., 1997, 60: 1-19

[22] Härdle W.. Applied Nonparametric Regression, 1990, Cambridge, New York: Cambridge University Press

[23] Härdle W., Liang H., Gao J. T.. Partially Linear Models, 2000, Heidelberg: Physica-Verlag

[24] Hwang J. T.. , Multiplicative errors-in-variables models with applications to recent data released by the U.S. department of energy. J. Amer. Statist. Assoc., 1986, 81: 680-688

[25] Iturria S. J., Carroll R. J., Firth D.. Polynomial regression and estimating functions in the presence of multiplicative measurement error. J. Roy. Statist. Soc. Ser. B, 1999, 61: 547-561

[26] Liang H.. Asymptotic normality of parametric part in partially linear models with measurement error in the nonparametric part. J. Statist. Plann. Infer., 2000, 86: 51-62

[27] Liang H., Härdle W., Carroll R. J.. Estimation in a semiparametric partially linear errors-in-variables model. Ann. Statist., 1999, 27: 1519-1535

[28] Rice J.. Convergence rates for partially splined models. Statist. Probab. Lett., 1986, 4: 203-208

[29] Robinson P. M.. Root-N-consistent semiparametric regression. Econometrica, 1988, 56: 931-954

[30] Shi P. D., Li G. Y.. A note on the convergence rates of M-estimates for partly linear model. Statistics, 1995, 26: 27-47

[31] Speckman P.. Kernel smoothing in partial linear models. J. Roy. Statist. Soc., Ser. B, 1988, 50: 413-436

[32] Tibshirani R.. Regression shrinkage and selection via the lasso. J. Roy. Statist. Soc. Ser. B, 1996, 58: 267-288

[33] You J. H., Xu Q.. Covariate selection for linear errors-in-variables regression models. Comm. Statist. Theory Methods, 2007, 36: 375-386

[34] Zhu L., Cui H.. A semiparametric regression model with errors in variables. Scand. J. Statist., 2003, 30: 429-442