Edgeworth expansions for semiparametric averaged derivatives

A valid Edgeworth expansion is established for the limit distribution of density-weighted semiparametric averaged derivative estimates of single index models. The leading term that corrects the normal limit varies in magnitude, depending on the choice of bandwidth and kernel order. In general this term has order larger than the n -½ that prevails in standard parametric problems, but we find circumstances in which it is O(n -½), thereby extending the achievement of an n -½ Berry-Essen bound in Robinson (1995). A valid empirical Edgeworth expansion is also established. We also provide theoretical and empirical Edgeworth expansions for a studentized statistic, where the correction terms are different from those for the unstudentized case. We report a Monte Carlo study of finite sample performance.

[1]  P. Robinson.  ROOT-N-CONSISTENT SEMIPARAMETRIC REGRESSION , 1988 .

[2]  Oliver Linton,et al.  SECOND ORDER APPROXIMATION IN THE PARTIALLY LINEAR REGRESSION MODEL , 1995 .

[3]  P. Hall,et al.  On the Distribution of a Studentized Quantile , 1988 .

[4]  The approximate distribution of nonparametric regression estimates , 1995 .

[5]  A. Tsybakov,et al.  Bandwidth Choice for Average Derivative Estimation , 1992 .

[6]  Yoshihiko Nishiyama,et al.  Studentization in Edgworth Expansions for Estimates of Semiparametric Index Models - (Now Published in C Hsiao, K Morimune and J Powell (Eds): Nonlinear Statistical Modeling (Festschrift for Takeshi Amemiya), (Cambridge University Press, 2001), Pp.197-240.) , 1999 .

[7]  A. L. Nagar.  The Bias and Moment Matrix of the General k-Class Estimators of the Parameters in Simultaneous Equations , 1959 .

[8]  Whitney K. Newey,et al.  EFFICIENT INSTRUMENTAL VARIABLES ESTIMATION OF NONLINEAR MODELS , 1990 .

[9]  J. Pfanzagl.  TheBerry-Esseen bound for minimum contrast estimates , 1971 .

[10]  S. Dharmadhikari,et al.  Bounds on the Moments of Martingales , 1968 .

[11]  P. Robinson.  The Normal Approximation for Semiparametric Averaged Derivatives , 1995 .

[12]  Charles F. Manski,et al.  Adaptive estimation of non–linear regression models , 1984 .

[13]  A. Tsybakov,et al.  How sensitive are average derivatives , 1993 .

[14]  O. Linton.  Edgeworth Approximation for MINPIN Estimators in Semiparametric Regression Models , 1994, Econometric Theory.

[15]  F. Götze,et al.  The Edgeworth Expansion for $U$-Statistics of Degree Two , 1986 .

[16]  P. Robinson,et al.  Semiparametric estimation from time series with long-range dependence , 1994 .

[17]  Thomas M. Stoker,et al.  Optimal bandwidth choice for density-weighted averages , 1996 .

[18]  H. Callaert,et al.  An Edgeworth Expansion for $U$-Statistics , 1980 .

[19]  J. Sargan,et al.  A General Approximation to the Distribution of Instrumental Variables Estimates , 1971 .

[20]  Thomas M. Stoker,et al.  Semiparametric Estimation of Index Coefficients , 1989 .

[21]  Friedrich Götze,et al.  An Edgeworth expansion for symmetric statistics , 1997 .

[22]  P. Robinson.  Asymptotically efficient estimation in the presence of heteroskedasticity of unknown form , 1987 .

[23]  R. Helmers.  On the Edgeworth expansion and the bootstrap approximation for a studentized U-statistic , 1987 .

[24]  P. Robinson,et al.  Hypothesis Testing in Semiparametric and Nonparametric Models for Econometric Time Series , 1989 .