The Annals of Statistics

Nonparametric quasi-likelihood

Jeng-Min Chiou and Hans-Georg Müller

Full-text: Open access

Abstract

The quasi-likelihood function proposed by Wedderburn broadened the scope of generalized linear models by specifying the variance function in-stead of the entire distribution. However, complete specification of variance functions in the quasi-likelihood approach may not be realistic. We define a nonparametric quasi-likelihood by replacing the specified variance function in the conventional quasi-likelihood with a nonparametric variance function estimate. This nonparametric variance function estimate is based on squared residuals from an initial model fit. The rate of convergence of the nonparametric variance function estimator is derived. It is shown that the asymptotic limiting distribution of the vector of regression parameter estimates is the same as for the quasi-likelihood estimates obtained under correct specification of the variance function, thus establishing the asymptotic efficiency of the nonparametric quasi-likelihood estimates. We propose bandwidth selection strategies based on deviance and Pearson’s chi-square statistic. It is demonstrated in simulations that for finite samples the proposed nonparametric quasi-likelihood method can improve upon extended quasi-likelihood or pseudo-likelihood methods where the variance function is assumed to fall into a parametric class with unknown parameters. We illustrate the proposed methods with applications to dental data and cherry tree data.

Article information

Source
Ann. Statist., Volume 27, Number 1 (1999), 36-64.

Dates
First available in Project Euclid: 5 April 2002

Permanent link to this document
https://projecteuclid.org/euclid.aos/1018031100

Digital Object Identifier
doi:10.1214/aos/1018031100

Mathematical Reviews number (MathSciNet)
MR1701100

Zentralblatt MATH identifier
0978.62056

Subjects
Primary: 62G07: Density estimation 62G10: Hypothesis testing 62J12: Generalized linear models

Keywords
Variance function smoothing semiparametric modeling deviance bandwidth selection efficiency extended quasi-likelihood pseudo-likelihood

Citation

Chiou, Jeng-Min; Müller, Hans-Georg. Nonparametric quasi-likelihood. Ann. Statist. 27 (1999), no. 1, 36--64. doi:10.1214/aos/1018031100. https://projecteuclid.org/euclid.aos/1018031100


Export citation

References

  • Atkinson, A. C. (1987). Plots, Transformations, and Regression. Clarendon Press, Oxford.
  • Carroll, R. J. and Ruppert, D. (1982). Robust estimation in heteroscedastic linear models. Ann. Statist. 10 429-441.
  • Chiou, J.-M. and M ¨uller, H.-G. (1998). Quasi-likelihood regression with unknown link and variance functions. J. Amer. Statist. Assoc. 93 1376-1387.
  • Davidian, M. and Carroll, R. J. (1988). A note on extended quasi-likelihood. J. Roy. Statist. Soc. Ser. B 50 74-82.
  • Fahrmeir, L. (1990). Maximum likelihood estimation in misspecified generalized linear models. Statistics 21 487-502. Fan, J. and Gijbels, I. (1996) Local Polynomial Modeling and Its Applications. Chapman and Hall, London. Fan, J. and Truong, Y. K. (1993) Nonparametric regression with errors-in-variables. Ann. Statist. 21 1900-1925.
  • Hall, P. and Carroll, R. J. (1989). Variance function estimation: The effect of estimating the mean. J. Roy. Statist. Soc. Ser. B 51 3-14.
  • Hall, P., Kay, J. W. and Titterington, D. M. (1990). Asymptotically optimal difference-based estimation of variance in nonparametric regression. Biometrika 77 521-528.
  • McCullagh, P. (1983). Quasi-likelihood functions. Ann. Statist. 11 59-67. McCullagh, P. and Nelder, J. A. (1989) Generalized Linear Models. Chapman and Hall, London. M ¨uller, H.-G. (1988) Nonparametric regression analysis of longitudinal data. Lecture Notes in Statist. 46. Springer, New York.
  • M ¨uller, H.-G. and Stadtm ¨uller, U. (1987). Estimation of heteroscedasticity in regression analysis. Ann. Statist. 15 610-625.
  • M ¨uller, H.-G. and Stadtm ¨uller, U. (1993). On variance function estimation with quadratic forms. J. Statist. Plann. Inference 35 213-231.
  • M ¨uller, H.-G. and Zhao, P.-L. (1995). On a semiparametric variance function model and a test for heteroscedasticity. Ann. Statist. 23 946-967.
  • Nelder, J. A. and Lee, Y. (1992). Likelihood, quasi-likelihood and pseudo-likelihood: Some comparisons. J. Roy. Statist. Soc. Ser. B 54 273-284.
  • Nelder, J. A. and Pregibon, P. (1987). An extended quasi-likelihood function. Biometrika 74 221-232. Nelder, J. A. and Wedderburn, R. W. M. (1972) Generalized linear models. J. Roy. Statist. Soc. Sec. A 135 370-384.
  • Ruppert, D., Wand, M. P., Holst, U. and H ¨ossjer, O. (1997). Local polynomial variance function estimation. Technometrics 39 262-273.
  • Ryan, T., Joiner, B. and Ryan, B. (1985). Minitab Student Handbook, 2nd ed. Duxbury, Belmont, CA.
  • Silverman, B. W. (1985). Some aspects of the spline smoothing approach to non-parametric regression curve fitting (with discussion). J. Roy. Statist. Soc. Ser. B 47 1-52.
  • Thompson, A. M., Brown, J. C., Kay, J. W. and Titterington, D. M. (1991). A study of methods of choosing the smoothing parameter in image restoration by regularization. IEEE Trans. Pattern Recognition Machine Intell. 13 326-338.
  • Titterington, D. M. (1985). Common structure of smoothing techniques in statistics. Internat. Statist. Rev. 53 141-170.
  • Wedderburn, R. W. M. (1974). Quasi-likelihood functions, generalized linear models and Gauss- Newton method. Biometrika 61 439-447.
  • Weisberg, S. and Welsh, A. H. (1994). Adapting for the missing link. Ann. Statist. 22 1674-1700.