Hostname: page-component-cd9895bd7-jkksz Total loading time: 0 Render date: 2024-12-27T18:14:22.246Z Has data issue: false hasContentIssue false
  • English
  • Français

Partially Adaptive Estimation of Regression Models via the Generalized T Distribution

Published online by Cambridge University Press:  18 October 2010

James B. McDonald  and
Whitney K. Newey
James B. McDonald
Affiliation:
Brigham Young University
Whitney K. Newey
Affiliation:
Princeton University
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper considers M-estimators of regression parameters that make use of a generalized functional form for the disturbance distribution. The family of distributions considered is the generalized t (GT), which includes the power exponential or Box-Tiao, normal, Laplace, and t distributions as special cases. The corresponding influence function is bounded and redescending for finite “degrees of freedom.” The regression estimators considered are those that maximize the GT quasi-likelihood, as well as one-step versions. Estimators of the parameters of the GT distribution and the effect of such estimates on the asymptotic efficiency of the regression estimates are discussed. We give a minimum-distance interpretation of the choice of GT parameter estimate that minimizes the asymptotic variance of the regression parameters.

Type
Research Article
Information
Econometric Theory , Volume 4 , Issue 3 , December 1988 , pp. 428 - 457
Copyright
Copyright © Cambridge University Press 1988 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

1. Bates, C. & White, H.. A unified theory of consistent estimation for parametric models. Econometric Theory 1 (1985): 151–178.Google Scholar
2. Beran, R. Minimum hellinger distance estimation of parametric models. Annals of Statistics 5 (1977): 445–463.Google Scholar
3. Beran, R. Adaptive estimates for autoregressive processes. Annals of the Institute of Statistical Mathematics 28 (1977): 77–89.10.1007/BF02504731Google Scholar
4. Bickel, P.J. One-step Huber estimates in the linear model. Journal of the American Statistical Association 70 (1975): 428–434.10.1080/01621459.1975.10479884Google Scholar
5. Bickel, P.J. On adaptive estimation. Annals of Statistics 10 (1982): 647–671.10.1214/aos/1176345863Google Scholar
6. Bierens, H.J. Robust estimation and asymptotic theory in nonlinear econometrics. New York: Springer-Verlag, 1981.10.1007/978-3-642-45529-2Google Scholar
7. Goldfeld, S. & Quandt, R.E.. Econometrie modeling with nonnormal disturbances. Journal of Econometrics 17 (1981): 141–155.10.1016/0304-4076(81)90023-3Google Scholar
8. Hogg, R.V. Adaptive robust procedures: a partial review and some suggestions for future applications and theory. Journal of the American Statistical Association 69 (1974): 909–927.Google Scholar
9. Huber, P.J. Robust statistics. New York: Wiley, 1981.10.1002/0471725250Google Scholar
10. Huber, P.J. The behavior of maximum-likelihood estimates under nonstandard conditions. Proceedings of the Fifth Berkeley Symposium 1 (1967): 221–233.Google Scholar
11. Klein, R. & Spady, R.. Quasi-maximum likelihood as a parametric approach to robust estimation. Working paper, Bell Communications Research (1984).Google Scholar
12. Koenker, R. Robust estimation in econometrics. Econometric Reviews 1 (1982): 213–255.Google Scholar
13. Loeve, M. Probability theory I. New York: Springer-Verlag, 1977.Google Scholar
14. Manski, C. Adaptive estimation of nonlinear regression models. Econometric Reviews 3 (1984): 145–194.10.1080/07474938408800060Google Scholar
15. McDonald, J.B. Some generalized functions for the size distribution of income. Econometrica 52 (1984): 647–663.10.2307/1913469Google Scholar
16. McDonald, J.B. & Newey, W.K.. A generalized stochastic specification in econometric models. Brigham Young University mimeo (1984).Google Scholar
17. Missiakoulis, S. Sargan densities: which one. Journal of Econometrics 23 (1983): 223–233.10.1016/0304-4076(93)90078-JGoogle Scholar
18. Newey, W.K. Generic uniqueness of the population quasi-maximum likelihood parameters. mimeo, Princeton University (1986).Google Scholar
19. Newey, W.K. Adaptive estimation of regression models via moment restrictions. Journal of Econometrics 38 (1988): 301–339.Google Scholar
20. Pollard, D. New ways to prove central-limit theorems. Econometric Theory 1 (1985): 295–314.10.1017/S0266466600011233Google Scholar
21. Pötshcer, B.M. & Prucha, I.R.. A class of partially adaptive one-step M-estimators for the nonlinear regression model with dependent observations. Journal of Econometrics 25 (1986): 219–251.10.1016/0304-4076(86)90039-4Google Scholar
22. Pötshcer, B.M. & Prucha, I.R.. Consistency in nonlinear econometrics: a generic uniform law of large numbers and some comments on recent results, mimeo, University of Maryland (1986).Google Scholar
23. Prucha, I.R. & Kelejian, H.R.. The structure of simultaneous equations estimators: a generalization toward nonormal disturbances. Econometrica 52 (1984): 721–736.Google Scholar
24. White, H. Nonlinear regression on cross-section data. Econometrica 48 (1980): 721–746.Google Scholar
25. Wolfowitz, J. The minimum distance method. Annals of Mathematical Statistics 28 (1957): 75–88.10.1214/aoms/1177707038Google Scholar
26. Zeckhauser, R. & Thompson, M.. Linear regression with nonnormal error terms. Review of Economics and Statistics 52 (1970): 280–286.Google Scholar