A NEW ASYMPTOTIC THEORY FOR HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTS

A new first-order asymptotic theory for heteroskedasticity-autocorrelation (HAC) robust tests based on nonparametric covariance matrix estimators is developed. The bandwidth of the covariance matrix estimator is modeled as a fixed proportion of the sample size. This leads to a distribution theory for HAC robust tests that explicitly captures the choice of bandwidth and kernel. This contrasts with the traditional asymptotics (where the bandwidth increases more slowly than the sample size) where the asymptotic distributions of HAC robust tests do not depend on the bandwidth or kernel. Finite-sample simulations show that the new approach is more accurate than the traditional asymptotics. The impact of bandwidth and kernel choice on size and power of t-tests is analyzed. Smaller bandwidths lead to tests with higher power but greater size distortions, and large bandwidths lead to tests with lower power but smaller size distortions. Size distortions across bandwidths increase as the serial correlation in the data becomes stronger. Overall, the results clearly indicate that for bandwidth and kernel choice there is a trade-off between size distortions and power. Finite-sample performance using the new asymptotics is comparable to the bootstrap, which suggests that the asymptotic theory in this paper could be useful in understanding the theoretical properties of the bootstrap when applied to HAC robust tests.We thank an editor and a referee for constructive comments on a previous version of the paper. Helpful comments provided by Cliff Hurvich, Andy Levin, Jeff Simonoff, and seminar participants at NYU (Statistics), U. Texas Austin, Yale, U. Montreal, UCSD, UC Riverside, UC Berkeley, U. of Pittsburgh, SUNY Albany, U. Aarhus, Brown U., NBER/NSF Time Series Conference, and 2003 Winter Meetings of the Econometrics Society are gratefully acknowledged. We gratefully acknowledge financial support from the National Science Foundation through grant SES-0095211. We thank the Center for Analytic Economics at Cornell University.

[1]  W. Newey,et al.  Automatic Lag Selection in Covariance Matrix Estimation , 1994 .

[2]  Hans R. Künsch,et al.  Second-order correctness of the blockwise bootstrap for stationary observations , 1996 .

[3]  Serena Ng,et al.  The Exact Error In Estimating The Spectral Density At The Origin , 1996 .

[4]  Joel L. Horowitz,et al.  Bootstrap Critical Values for Tests Based on Generalized-Method-of-Moments Estimators , 1996 .

[5]  Nicholas M. Kiefer,et al.  Simple Robust Testing of Hypotheses in Nonlinear Models , 2001 .

[6]  J. Magnus,et al.  Matrix Differential Calculus with Applications in Statistics and Econometrics (Revised Edition) , 1999 .

[7]  Nicholas M. Kiefer,et al.  Simple Robust Testing of Regression Hypotheses , 2000 .

[8]  A. C. Davison,et al.  ON STUDENTIZING AND BLOCKING METHODS FOR IMPLEMENTING THE BOOTSTRAP WITH DEPENDENT DATA , 1993 .

[9]  Nicholas M. Kiefer,et al.  HETEROSKEDASTICITY-AUTOCORRELATION ROBUST STANDARD ERRORS USING THE BARTLETT KERNEL WITHOUT TRUNCATION , 2002 .

[10]  W. Newey,et al.  Large sample estimation and hypothesis testing , 1986 .

[11]  Atsushi Inoue,et al.  Bootstrapping GMM estimators for time series , 2003 .

[12]  L. Hansen.  Large Sample Properties of Generalized Method of Moments Estimators , 1982 .

[13]  Spectral Density Estimation and Robust Hypothesis Testing Using Steep Origin Kernels Without Truncation , 2004 .

[14]  K. Berk.  Consistent Autoregressive Spectral Estimates , 1974 .

[15]  Andrew T. Levin,et al.  A Practitioner's Guide to Robust Covariance Matrix Estimation , 1996 .

[16]  H. R. K. unsch,et al.  Second Order Correctness of the Blockwise Bootstrap for Stationary Observations , 1996 .

[17]  P. Phillips,et al.  Multiple Time Series Regression with Integrated Processes , 1986 .

[18]  Matthew J. Cushing,et al.  Covariance matrix estimation , 1999 .

[19]  C. Heyde.  Quasi-likelihood and its application : a general approach to optimal parameter estimation , 1998 .

[20]  H. White.  Asymptotic theory for econometricians , 1985 .

[21]  A. Gallant,et al.  Nonlinear Statistical Models , 1988 .

[22]  Ulrich K. Müller.  A theory of robust long-run variance estimation , 2007 .

[23]  Nicholas M. Kiefer,et al.  HETEROSKEDASTICITY-AUTOCORRELATION ROBUST TESTING USING BANDWIDTH EQUAL TO SAMPLE SIZE , 2002, Econometric Theory.

[24]  C. R. Rao,et al.  Handbook of Statistics 15: Robust Inference , 2000, Technometrics.

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

[26]  Michael Jansson.  The Error in Rejection Probability of Simple Autocorrelation Robust Tests , 2004 .

[27]  Michael Jansson.  CONSISTENT COVARIANCE MATRIX ESTIMATION FOR LINEAR PROCESSES , 2002, Econometric Theory.

[28]  O. Papasouliotis,et al.  Covariance Matrix Estimation , 2006 .

[29]  C. Heyde,et al.  Quasi-likelihood and its application , 1997 .

[30]  C. Velasco,et al.  EDGEWORTH EXPANSIONS FOR SPECTRAL DENSITY ESTIMATES AND STUDENTIZED SAMPLE MEAN , 2000, Econometric Theory.

[31]  P. Phillips,et al.  Improved Har Inference Using Power Kernels Without Truncation , 2005 .

[32]  J. Davidson,et al.  Consistency of Kernel Estimators of Heteroscedastic and Autocorrelated Covariance Matrices , 2000 .

[33]  E. Ziegel.  Matrix Differential Calculus With Applications in Statistics and Econometrics , 1989 .

[34]  Paolo Paruolo,et al.  Simple Robust Testing of Regression Hypotheses: A Comment , 2001 .

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

[36]  P. Robinson.  Inference-without-Smoothing in the Presence of Nonparametric Autocorrelation - (Now published in 'Econometrica', 66 (1998), pp.1163-1182.) , 1997 .

[37]  D. B. Preston.  Spectral Analysis and Time Series , 1983 .

[38]  D. Cox,et al.  Asymptotic techniques for use in statistics , 1989 .

[39]  Donald W. K. Andrews,et al.  An Improved Heteroskedasticity and Autocorrelation Consistent Covariance Matrix Estimator , 1992 .

[40]  T. Vogelsang.  TESTING IN GMM MODELS WITHOUT TRUNCATION , 2003 .

[41]  Bruce E. Hansen,et al.  Consistent Covariance Matrix Estimation for Dependent Heterogeneous Processes , 1992 .

[42]  H. White,et al.  A Unified Theory of Estimation and Inference for Nonlinear Dynamic Models , 1988 .

[43]  Jeffrey S. Simonoff,et al.  The relative importance of bias and variability in the estimation of the variance of a statistic , 1993 .

[44]  P. Phillips,et al.  Spectral Density Estimation and Robust Hypothesis Testing Using Steep Origin Kernels Without Truncation , 2006 .

[45]  N. Kiefer,et al.  Simple Robust Testing of Hypotheses in Non-Linear Models , 1998 .

[46]  P. Phillips,et al.  Consistent Hac Estimation and Robust Regression Testing Using Sharp Origin Kernels with No Truncation , 2003 .

[47]  W. D. Haan.  VECTOR AUTOREGRESSIVE COVARIANCE MATRIX ESTIMATION , 2003 .

[48]  AN IMPROVED FORMULA FOR THE ASYMPTOTIC VARIANCE OF SPECTRUM ESTIMATES , 1970 .

[49]  Helle Bunzel,et al.  Powerful Trend Function Tests That Are Robust to Strong Serial Correlation, With an Application to the Prebisch–Singer Hypothesis , 2005 .