Efficient estimation for time-varying coefficient longitudinal models

ABSTRACT For estimation of time-varying coefficient longitudinal models, the widely used local least-squares (LS) or covariance-weighted local LS smoothing uses information from the local sample average. Motivated by the fact that a combination of multiple quantiles provides a more complete picture of the distribution, we investigate quantile regression-based methods to improve efficiency by optimally combining information across quantiles. Under the working independence scenario, the asymptotic variance of the proposed estimator approaches the Cramér–Rao lower bound. In the presence of dependence among within-subject measurements, we adopt a prewhitening technique to transform regression errors into independent innovations and show that the prewhitened optimally weighted quantile average estimator asymptotically achieves the Cramér–Rao bound for the independent innovations. Fully data-driven bandwidth selection and optimal weights estimation are implemented through a two-step procedure. Monte Carlo studies show that the proposed method delivers more robust and superior overall performance than that of the existing methods.

[1]  本田 純久.  Longitudinal Data , 2003, Encyclopedia of Wireless Networks.

[2]  Naomi S. Altman,et al.  Quantile regression , 2019, Nature Methods.

[3]  P. Solli,et al.  Longitudinal studies. , 2015, Journal of thoracic disease.

[4]  Zhibiao Zhao,et al.  EFFICIENT REGRESSIONS VIA OPTIMALLY COMBINING QUANTILE INFORMATION , 2014, Econometric Theory.

[5]  Jianqing Fan,et al.  Penalized composite quasi‐likelihood for ultrahigh dimensional variable selection , 2009, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[6]  Runze Li,et al.  Local composite quantile regression smoothing: an efficient and safe alternative to local polynomial regression , 2010 .

[7]  Jianhui Zhou,et al.  Quantile regression in partially linear varying coefficient models , 2009, 0911.3501.

[8]  Local linear regression for data with AR errors , 2009, Acta mathematicae applicatae Sinica.

[9]  Mendel Fygenson,et al.  INFERENCE FOR CENSORED QUANTILE REGRESSION MODELS IN LONGITUDINAL STUDIES , 2009, 0904.0080.

[10]  Zhongyi Zhu,et al.  On the asymptotics of marginal regression splines with longitudinal data , 2008 .

[11]  Zongwu Cai,et al.  Nonparametric Quantile Estimations for Dynamic Smooth Coefficient Models , 2008 .

[12]  H. Zou,et al.  Composite quantile regression and the oracle Model Selection Theory , 2008, 0806.2905.

[13]  Mi-Ok Kim,et al.  Quantile regression with varying coefficients , 2007, 0708.0471.

[14]  Xuming He,et al.  Conditional growth charts , 2006 .

[15]  Kani Chen,et al.  Local polynomial regression analysis of clustered data , 2005 .

[16]  R. Koenker.  Quantile Regression: Name Index , 2005 .

[17]  R. Koenker.  Quantile regression for longitudinal data , 2004 .

[18]  J. Ware,et al.  Applied Longitudinal Analysis , 2004 .

[19]  Toshio Honda,et al.  Quantile regression in varying coefficient models , 2004 .

[20]  S. Sheather.  Density Estimation , 2004 .

[21]  W. Fung,et al.  Median regression for longitudinal data , 2003, Statistics in medicine.

[22]  E. Mammen,et al.  More Efficient Local Polynomial Estimation in Nonparametric Regression With Autocorrelated Errors , 2003 .

[23]  Kai F. Yu,et al.  Nonparametric varying-coefficient models for the analysis of longitudinal data , 2002 .

[24]  Zhongyi Zhu,et al.  Estimation in a semiparametric model for longitudinal data with unspecified dependence structure , 2002 .

[25]  Jianqing Fan,et al.  Two‐step estimation of functional linear models with applications to longitudinal data , 1999 .

[26]  Chin-Tsang Chiang,et al.  Asymptotic Confidence Regions for Kernel Smoothing of a Varying-Coefficient Model With Longitudinal Data , 1998 .

[27]  Li Ping Yang,et al.  Nonparametric smoothing estimates of time-varying coefficient models with longitudinal data , 1998 .

[28]  M. C. Jones,et al.  Local Linear Quantile Regression , 1998 .

[29]  P. Diggle,et al.  Semiparametric models for longitudinal data with application to CD4 cell numbers in HIV seroconverters. , 1994, Biometrics.

[30]  Jianqing Fan,et al.  Local polynomial modelling and its applications , 1994 .

[31]  David Wypij,et al.  Pulmonary function between 6 and 18 years of age , 1993, Pediatric pulmonology.

[32]  B. Silverman,et al.  Estimating the mean and covariance structure nonparametrically when the data are curves , 1991 .

[33]  Roger Koenker,et al.  Adaptive $L$-Estimation for Linear Models , 1989 .

[34]  Roger Koenker,et al.  A note on L-estimates for linear models , 1984 .

[35]  C S Berkey,et al.  Distribution of forced vital capacity and forced expiratory volume in one second in children 6 to 11 years of age. , 1983, The American review of respiratory disease.

[36]  S. Gould.  ALLOMETRY AND SIZE IN ONTOGENY AND PHYLOGENY , 1966, Biological reviews of the Cambridge Philosophical Society.

[37]  A. J. Stam.  Some Inequalities Satisfied by the Quantities of Information of Fisher and Shannon , 1959, Inf. Control..