Smoothed Quantile Regression for Panel Data

This paper studies fixed effects estimation of quantile regression models for panel data. Under an asymptotic framework where both the numbers of individuals and time periods grow at the same rate, we show that the fixed-effects estimator for the smoothed objective function has a limiting normal distribution with a bias in the mean, and provide the analytic form of the asymptotic bias. We propose a one-step bias correction estimator based on the analytic bias formula obtained from the asymptotic analysis. Importantly, our results cover the case that observations are dependent over time. We illustrate the effects of the bias correction through simulations.

[1]  Jinyong Hahn,et al.  BIAS REDUCTION FOR DYNAMIC NONLINEAR PANEL MODELS WITH FIXED EFFECTS , 2011, Econometric Theory.

[2]  Hans-Georg Müller,et al.  Smooth Optimum Kernel Estimators of Densities, Regression Curves and Modes , 1984 .

[3]  P. Massart,et al.  About the constants in Talagrand's concentration inequalities for empirical processes , 2000 .

[4]  E. Eberlein.  Weak convergence of partial sums of absolutely regular sequences , 1984 .

[5]  Aman Ullah,et al.  The second-order bias and mean squared error of nonlinear estimators , 1996 .

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

[7]  Iván Fernández-Val,et al.  Panel Data Models with Nonadditive Unobserved Heterogeneity: Estimation and Inference , 2012, 1206.2966.

[8]  Victor Chernozhukov,et al.  Quantile Regression Under Misspecification, with an Application to the U.S. Wage Structure , 2004 .

[9]  R. Koenker.  Quantile Regression: Quantile Regression in R: A Vignette , 2005 .

[10]  Stéphane Bonhomme,et al.  Robust priors in nonlinear panel data models , 2007 .

[11]  Geert Dhaene,et al.  Split-Panel Jackknife Estimation of Fixed-Effect Models , 2015 .

[12]  Carlos Lamarche,et al.  Estimation of Censored Quantile Regression for Panel Data With Fixed Effects , 2013 .

[13]  Peter C. B. Phillips,et al.  A Shortcut to LAD Estimator Asymptotics , 1991, Econometric Theory.

[14]  W. Newey,et al.  Average and Quantile Effects in Nonseparable Panel Models , 2009, 0904.1990.

[15]  Jinyong Hahn,et al.  Asymptotically Unbiased Inference for a Dynamic Panel Model with Fixed Effects When Both N and T are Large , 2000 .

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

[17]  Stéphane Bonhomme,et al.  Nonlinear Panel Data Estimation via Quantile Regressions , 2015 .

[18]  D. Andrews.  Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimation , 1991 .

[19]  W. Newey,et al.  A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelationconsistent Covariance Matrix , 1986 .

[20]  Jason Abrevaya,et al.  The Effects of Birth Inputs on Birthweight , 2008 .

[21]  J. Horowitz.  A Smoothed Maximum Score Estimator for the Binary Response Model , 1992 .

[22]  M. Talagrand.  Sharper Bounds for Gaussian and Empirical Processes , 1994 .

[23]  T. Lancaster.  The incidental parameter problem since 1948 , 2000 .

[24]  J. Hahn,et al.  The incidental parameter problem in a non-differentiable panel data model , 2009 .

[25]  Christopher Timmins,et al.  The Impact of Piped Water Provision on Infant Mortality in Brazil: a Quantile Panel Data Approach , 2007 .

[26]  Adam M. Rosen,et al.  Set identification via quantile restrictions in short panels , 2009 .

[27]  M. A. Arcones,et al.  Second Order Representations of the Least Absolute Deviation Regression Estimator , 1998 .

[28]  Ken-ichi Yoshihara.  Moment inequalities for mixing sequences , 1978 .

[29]  Jinyong Hahn,et al.  JACKKNIFE AND ANALYTICAL BIAS REDUCTION FOR NONLINEAR PANEL MODELS , 2003 .

[30]  E. Giné,et al.  On consistency of kernel density estimators for randomly censored data: rates holding uniformly over adaptive intervals , 2001 .

[31]  Keith Knight,et al.  Limiting distributions for $L\sb 1$ regression estimators under general conditions , 1998 .

[32]  K. Yoshihara.  Limiting behavior of U-statistics for stationary, absolutely regular processes , 1976 .

[33]  J. Neyman,et al.  Consistent Estimates Based on Partially Consistent Observations , 1948 .

[34]  Donggyu Sul,et al.  Bias in Dynamic Panel Estimation with Fixed Effects, Incidental Trends and Cross Section Dependence , 2003 .

[35]  Christian Hansen,et al.  A Penalty Function Approach to Bias Reduction in Non-Linear Panel Models with Fixed Effects , 2005 .

[36]  Kengo Kato,et al.  Asymptotics for panel quantile regression models with individual effects , 2012 .

[37]  J. Horowitz.  Bootstrap Methods for Median Regression Models , 1996 .

[38]  M. A. Arcones,et al.  Central limit theorems for empirical andU-processes of stationary mixing sequences , 1994 .

[39]  Jinyong Hahn,et al.  Understanding Bias in Nonlinear Panel Models: Some Recent Developments ∗ , 2005 .

[40]  Jason Abrevaya,et al.  The effects of birth inputs on birthweight : evidence from quantile estimation on panel data by , 2007 .

[41]  D. Pollard,et al.  $U$-Processes: Rates of Convergence , 1987 .

[42]  Antonio F. Galvao,et al.  Asymptotics and bootstrap inference for panel quantile regression models with fixed effects , 2010 .

[43]  W. Newey,et al.  Nonparametric identification in panels using quantiles , 2013, 1312.4094.

[44]  Bruce G. Lindsay,et al.  Efficiency of projected score methods in rectangular array asymptotics , 2003 .

[45]  S. Lipsitz,et al.  Quantile Regression Methods for Longitudinal Data with Drop‐outs: Application to CD4 Cell Counts of Patients Infected with the Human Immunodeficiency Virus , 1997 .

[46]  Moshe Buchinsky.  Estimating the asymptotic covariance matrix for quantile regression models a Monte Carlo study , 1995 .

[47]  Jianqing Fan.  Nonlinear Time Series , 2003 .

[48]  M. Talagrand.  New concentration inequalities in product spaces , 1996 .

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

[50]  Joel L. Horowitz,et al.  Bandwidth Selection in Semiparametric Estimation of Censored Linear Regression Models , 1990, Econometric Theory.

[51]  Bin Yu.  RATES OF CONVERGENCE FOR EMPIRICAL PROCESSES OF STATIONARY MIXING SEQUENCES , 1994 .

[52]  Bin Yu.  Density Estimation in the $L^\infty$ Norm for Dependent Data with Applications to the Gibbs Sampler , 1993 .

[53]  J. Horowitz.  The bootstrap in econometrics , 2003 .

[54]  Tiemen Woutersen.  Robustness against Incidental Parameters , 2002 .

[55]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[56]  E. Giné,et al.  Rates of strong uniform consistency for multivariate kernel density estimators , 2002 .

[57]  Ivan A. Canay.  A Simple Approach to Quantile Regression for Panel Data , 2011 .

[58]  E. Parzen.  On Consistent Estimates of the Spectrum of a Stationary Time Series , 1957 .

[59]  D. Chetverikov,et al.  IV Quantile Regression for Group-Level Treatments, with an Application to the Effects of Trade on the Distribution of Wages , 2013 .

[60]  Iván Fernández-Val,et al.  Bias Correction in Panel Data Models with Individual Specific Parameters , 2005 .

[61]  R. Koenker,et al.  Regression Quantiles , 2007 .

[62]  Takeshi Amemiya,et al.  Two Stage Least Absolute Deviations Estimators , 1982 .

[63]  Hidehiko Ichimura,et al.  Implementing Nonparametric and Semiparametric Estimators , 2006 .

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