Optimal Smoothing for a Computationally and Statistically Efficient Single Index Estimator

  • Yingcun Xia
  • Wolfgang Karl Härdle
  • Oliver Linton


In semiparametric models it is a common approach to under-smooth the nonparametric functions in order that estimators of the finite dimensional parameters can achieve root-n consistency. The requirement of under-smoothing may result, as we show, from inefficient estimation methods or technical difficulties. Xia et al. (J. Roy. Statist. Soc. B. 64:363–410, 2002) proposed an adaptive method for the multiple-index model, called MAVE. In this chapter we further refine the estimation method. Under some conditions, our estimator of the single-index is asymptotically normal and most efficient in the semi-parametric sense. Moreover, we derive higher-order expansions for our estimator and use them to define an optimal bandwidth for the purposes of index estimation. As a result we obtain a practically more relevant method and we show its superior performance in a variety of applications.


Link Function Optimal Bandwidth High Order Property Slice Inverse Regression Good Bandwidth 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The first author is most grateful to Professor V. Spokoiny for helpful discussions and NUS RMI for support. The second author thanks the Deutsche Forschungsgemeinschaft SFB 649 “Ökonomisches Risiko” for financial support. The third author thanks the ESRC for financial support.


  1. Bickel, P., Klaassen, A.J., Ritov, Y., & Wellner, J.A. (1993). Efficient and adaptive inference in semiparametric models. Baltimore: Johns Hopkins University Press.Google Scholar
  2. Carroll, R.J., Fan. J., Gijbels, I., & Wand, M.P. (1997). Generalized partially linear single-index models. Journal of American Statistical Association, 92, 477–489.MathSciNetMATHCrossRefGoogle Scholar
  3. de la Peña, V.H. (1999) A general class of exponential inequalities for martingales and ratios. The Annals of Probability, 27, 537–564.MathSciNetMATHCrossRefGoogle Scholar
  4. Delecroix, M., Härdle, W., & Hristache, M. (2003). Efficient estimation in conditional single-index regression. Journal of Multivariate Analysis, 86, 213–226.MathSciNetMATHCrossRefGoogle Scholar
  5. Delecroix, M., Hristache, M., & Patilea, V. (2006). On semiparametric M-estimation in single-index regression. Journal of Statistical Planning and Inference, 136, 730–769.MathSciNetMATHCrossRefGoogle Scholar
  6. Fan, J., & Gijbels, I. (1996). Local polynomial modeling and its applications. London: Chapman & Hall.Google Scholar
  7. Fan, J., & Yao, Q. (2003). Nonlinear time series: nonparametric and parametric methods. New York: Springer.MATHCrossRefGoogle Scholar
  8. Friedman, J.H. (1984). SMART User’s Guide. Laboratory for Computational Statistics, Stanford University Technical Report No. 1.Google Scholar
  9. Hall, P. (1989). On projection pursuit regression. Annals of Statistics, 17, 573–588.MathSciNetMATHCrossRefGoogle Scholar
  10. Härdle, W., Hall, P., & Ichimura, H. (1993). Optimal smoothing in single-index models. Annals of Statistics, 21, 157–178.MathSciNetMATHCrossRefGoogle Scholar
  11. Härdle, W., & Stoker, T.M. (1989) Investigating smooth multiple regression by method of average derivatives. Journal of American Statistical Association, 84 986–995.MATHGoogle Scholar
  12. Härdle, W., & Tsybakov, A.B. (1993). How sensitive are average derivatives? Journal of Econometrics, 58, 31–48.MathSciNetMATHCrossRefGoogle Scholar
  13. Horowitz, J.L. & Härdle, W. (1996) Direct semiparametric estimation of single-index models with discrete covariates. Journal of American Statistical Association, 91, 1632–1640.MATHCrossRefGoogle Scholar
  14. Hristache, M., Juditsky, A., & Spokoiny, V. (2001) Direct estimation of the single-index coefficients in single-index models. Annals of Statistics29, 1–32.Google Scholar
  15. Hristache, M., Juditsky, A., & Spokoiny, V. (2002). Direct estimation of the index coefficient in a single-index model. Annals of Statistics, 29, 593–623.Google Scholar
  16. Ichimura, H. (1993). Semiparametric least squares (SLS) and weighted SLS estimation of single-index models. Journal of Econometrics, 58, 71–120.MathSciNetMATHCrossRefGoogle Scholar
  17. Li, K.C. (1991). Sliced inverse regression for dimension reduction (with discussion). Journal of American Statistical Association, 86, 316–342.MATHCrossRefGoogle Scholar
  18. Li, K.C. (1992). On principal Hessian directions for data visualization and dimension reduction: another application of Stein’s lemma. Journal of American Statistical Association, 87, 1025–1039.MATHCrossRefGoogle Scholar
  19. Linton, O. (1995) Second order approximation in the partially linear regression model. Econometrica, 63, 1079–1112.MathSciNetMATHCrossRefGoogle Scholar
  20. Nishiyama, Y., & Robinson, P.M. (2000). Edgeworth expansions for semiparametric average derivatives. Econometrica, 68, 931–980.MATHCrossRefGoogle Scholar
  21. Nishiyama, Y., & Robinson, P.M. (2005). The bootstrap and the Edgeworth correction for semiparametric average derivatives. Econometrica, 73, 903–948.MathSciNetMATHCrossRefGoogle Scholar
  22. Powell, J.L., Stock, J.H., & Stoker, T.M. (1989). Semiparametric estimation of index coefficients. Econometrica, 57, 1403–1430.MathSciNetMATHCrossRefGoogle Scholar
  23. Powell, J.L., & Stoker, T.M. (1996). Optimal bandwidth choice for density weighted averages. Journal of Econometrics, 755, 291–316.MathSciNetCrossRefGoogle Scholar
  24. Robinson, P. (1988). Root-N consistent semi-parametric regression. Econometrica, 156, 931–954.CrossRefGoogle Scholar
  25. Ruppert, D., Sheather, J., & Wand, P.M. (1995). An effective bandwidth selector for local least squares regression. Journal of American Statistical Association, 90, 1257–1270.MathSciNetMATHCrossRefGoogle Scholar
  26. Schott, J.R. (1997) Matrix analysis for statistics. New York: Wiley.MATHGoogle Scholar
  27. Weisberg, S., & Welsh, A.H. (1994). Estimating the missing link functions, Annals of Statistics, 22, 1674–1700.MathSciNetMATHCrossRefGoogle Scholar
  28. Xia, Y., Tong, H., Li, W.K., & Zhu, L. (2002). An adaptive estimation of dimension reduction space (with discussion). Journal of the Royal Statistical Society Series B, 64, 363–410.MathSciNetMATHGoogle Scholar
  29. Xia, Y. (2006). Asymptotic distributions for two estimators of the single-index model. Econometric Theory, 22, 1112–1137.MathSciNetMATHCrossRefGoogle Scholar
  30. Xia, Y., & Li, W.K. (1999) On single-index coefficient regression models. Journal of American Statistical Association, 94, 1275–1285.MathSciNetMATHCrossRefGoogle Scholar
  31. Yin, X., & Cook, R.D. (2005). Direction estimation in single-index regressions. Biometrika, 92, 371–384.MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Yingcun Xia
    • 1
  • Wolfgang Karl Härdle
    • 2
  • Oliver Linton
    • 3
  1. 1.Department of Statistics and Applied Probability and Risk Management InstituteNational University of SingaporeSingaporeSingapore
  2. 2.C.A.S.E. Centre for Applied Statistics and Economics, School of Business and EconomicsHumboldt-Universität zu BerlinBerlinGermany
  3. 3.CambridgeUK

Personalised recommendations