×

zbMATH — the first resource for mathematics

Quasi-likelihood models and optimal inference. (English) Zbl 0853.62066
Summary: Consider an ergodic Markov chain on the real line, with parametric models for the conditional mean and variance of the transition distribution. Such a setting is an instance of a quasi-likelihood model. The customary estimator for the parameter is the maximum quasi-likelihood estimator. It is not efficient, but as good as the best estimator that ignores the parametric model for the conditional variance.
We construct two efficient estimators. One is a convex combination of solutions of two estimating equations, the other a weighted nonlinear one-step least squares estimator, with weights involving predictors for the third and fourth centered conditional moments of the transition distribution. Additional restrictions on the model can lead to further improvement. We illustrate this with an autoregressive model whose error variance is related to the autoregression parameter.

MSC:
62M05 Markov processes: estimation; hidden Markov models
62G20 Asymptotic properties of nonparametric inference
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] AMEMIy A, T. 1973. Regression analysis when the variance of the dependent variable is proportional to the square of its expectation. J. Amer. Statist. Assoc. 68 928 934. Z. JSTOR: · Zbl 0271.62085 · doi:10.2307/2284524 · links.jstor.org
[2] BICKEL, P. J. 1975. One-step Huber estimates in the linear model. J. Amer. Statist. Assoc. 70 428 434. Z. JSTOR: · Zbl 0322.62038 · doi:10.2307/2285834 · links.jstor.org
[3] BICKEL, P. J. 1993. Estimation in semiparametric models. In Multivariate Analy sis: Future Z. Directions C. R. Rao, ed. 55 73. North-Holland, Amsterdam. Z. · Zbl 0795.62027
[4] BICKEL, P. J., KLAASSEN, C. A. J., RITOV, Y. and WELLNER, J. A. 1993. Efficient and Adaptive Estimation for Semiparametric Models. Johns Hopkins Univ. Press. Z. · Zbl 0786.62001
[5] COLLOMB, G. 1984. Proprietes de convergence presque complete de predicteur a noy eau. \' \' Ź. Wahrsch. Verw. Gebiete 66 441 460. Z. · Zbl 0525.62046 · doi:10.1007/BF00533708
[6] CROWDER, M. 1986. On consistency and inconsistency of estimating equations. Econometric Theory 2 305 330. Z.
[7] CROWDER, M. 1987. On linear and quadratic estimating functions. Biometrika 74 591 597. Z. JSTOR: · Zbl 0635.62077 · doi:10.1093/biomet/74.3.591 · links.jstor.org
[8] FIRTH, D. 1987. On the efficiency of quasi-likelihood estimation. Biometrika 74 233 245. Z. JSTOR: · Zbl 0622.62034 · doi:10.1093/biomet/74.2.233 · links.jstor.org
[9] GODAMBE, V. P. 1985. The foundations of finite sample estimation in stochastic processes. Biometrika 72 419 428. Z. JSTOR: · Zbl 0584.62135 · doi:10.1093/biomet/72.2.419 · links.jstor.org
[10] GODAMBE, V. P. 1987. The foundations of finite sample estimation in stochastic processes. II. In Z Proceedings of the First World Congress of the Bernoulli Society Yu. Prohorov and V.. V. Sazonov, eds. 2 49 54. VNU Science Press, Utrecht. Z. · Zbl 0689.62074
[11] GODAMBE, V. P., ed. 1991. Estimating Functions. Oxford Univ. Press. Z. · Zbl 0745.00006
[12] GODAMBE, V. P. and HEy DE, C. C. 1987. Quasi-likelihood and optimal estimation. Internat. Statist. Rev. 55 231 244. Z. JSTOR: · Zbl 0671.62007 · doi:10.2307/1403403 · links.jstor.org
[13] GODAMBE, V. P. and THOMPSON, M. E. 1989. An extension of quasi-likelihood estimation. J. Statist. Plann. Inference 22 137 152. Z. · Zbl 0681.62036 · doi:10.1016/0378-3758(89)90106-7
[14] GREENWOOD, P. E. and WEFELMEy ER, W. 1990. Efficiency of estimators for partially specified filtered models. Stochastic Process. Appl. 36 353 370. Z. · Zbl 0719.62050 · doi:10.1016/0304-4149(90)90101-W
[15] GREENWOOD, P. E. and WEFELMEy ER, W. 1995. Efficiency of empirical estimators for Markov chains. Ann. Statist. 23 132 143. Z. · Zbl 0822.62067 · doi:10.1214/aos/1176324459
[16] HEy DE, C. C. 1987. On combining quasi-likelihood estimating functions. Stochastic Process. Appl. 25 281 287. Z. · Zbl 0636.62086 · doi:10.1016/0304-4149(87)90206-7
[17] HILL, J. R. and TSAI, C.-L. 1988. Calculating the efficiency of maximum quasilikelihood estimation. J. Roy Statist. Soc. Ser. C 37 219 230. JSTOR: · Zbl 04531330 · doi:10.2307/2347341 · links.jstor.org
[18] HINKLEY, D. V., REID, N. and SNELL, E. J., eds. 1991. Statistical Theory and Modelling. In Honour of Sir David Cox, FRS. Chapman and Hall, London. Z. · Zbl 0734.62001
[19] HOPFNER, R. 1993. On statistics of Markov step processes: representation of log-likelihood ratio \" processes in filtered local models. Probab. Theory Related Fields 94 375 398. Z. · Zbl 0766.62051 · doi:10.1007/BF01199249
[20] HOPFNER, R., JACOD, J. and LADELLI, L. 1990. Local asy mptotic normality and mixed normality \" for Markov statistical models. Probab. Theory Related Fields 86 105 129. Z. · Zbl 0685.60016 · doi:10.1007/BF01207516
[21] HUANG, W.-M. 1986. A characterization of limiting distributions of estimators in an autoregressive process. Ann. Inst. Statist. Math. 38 137 144. Z. · Zbl 0595.62088 · doi:10.1007/BF02482506
[22] HUBER, P. J. 1967. The behavior of maximum likelihood estimates under nonstandard conditions. Proc. Fifth Berkeley Sy mp. Math. Statist. Probab. 1 221 233. Univ. California Press, Berkeley. Z. · Zbl 0212.21504
[23] HUHTALA, K. 1992. A quasi-likelihood Markov model for the hardenability of steel. In Proc. Z. Sixth European Conference on Mathematics in Industry F. Hodnett, ed. 191 194. Teubner, Stuttgart. Z.
[24] HUTTON, J. E. and NELSON, P. I. 1986. Quasi-likelihood estimation for semimartingales. Stochastic Process. Appl. 22 245 257. Z. · Zbl 0616.62113 · doi:10.1016/0304-4149(86)90004-9
[25] JACOD, J. and SHIRy AEV, A. N. 1987. Limit Theorems for Stochastic Processes. Springer, Berlin. Z.
[26] KLIMKO, L. A. and NELSON, P. I. 1978. On conditional least squares estimation for stochastic processes. Ann. Statist. 6 629 642. Z. · Zbl 0383.62055 · doi:10.1214/aos/1176344207
[27] KREISS, J.-P. 1987. On adaptive estimation in autoregressive models when there are nuisance functions. Statist. Decisions 5 59 76. Z. · Zbl 0609.62123
[28] MCCULLAGH, P. and NELDER, J. A. 1989. Generalized Linear Models 2nd ed. Chapman and Hall, London. Z. · Zbl 0744.62098
[29] PENEV, S. 1991. Efficient estimation of the stationary distribution for exponentially ergodic Markov chains. J. Statist. Plann. Inference 27 105 123. Z. · Zbl 0727.62079 · doi:10.1016/0378-3758(91)90085-S
[30] ROUSSAS, G. G. 1965. Asy mptotic inference in Markov processes. Ann. Math. Statist. 36 987 992. Z. · Zbl 0138.11601 · doi:10.1214/aoms/1177700070
[31] THAVANESWARAN, A. and THOMPSON, M. E. 1986. Optimal estimation for semimartingales. J. Appl. Probab. 23 409 417. Z. JSTOR: · Zbl 0604.62082 · doi:10.2307/3214183 · links.jstor.org
[32] TRUONG, Y. K. and STONE, C. J. 1992. Nonparametric function estimation involving time series. Ann. Statist. 20 77 97. Z. · Zbl 0764.62038 · doi:10.1214/aos/1176348513
[33] WEDDERBURN, R. W. M. 1974. Quasi-likelihood functions, generalized linear models, and the Gauss Newton method. Biometrika 61 439 447. Z. JSTOR: · Zbl 0292.62050 · links.jstor.org
[34] WEFELMEy ER, W. 1993. Estimating functions and efficiency in a filtered model. In Frontiers in Z Pure and Applied Probability H. Niemi, G. Hognas, A. N. Shiry aev and A. V. \". Melnikov, eds. 1 287 295. VNU Science Press, Utrecht. Z. · Zbl 0810.62079
[35] WEFELMEy ER, W. 1994a. An efficient estimator for the expectation of a bounded function under the residual distribution of an autoregressive process. Ann. Inst. Statist. Math. 46 309 315.Z. · Zbl 0802.62084 · doi:10.1007/BF01720587
[36] WEFELMEy ER, W. 1994b. Improving maximum quasi-likelihood estimators. In Asy mptotic Z. Statistics P. Mandl and M. Huskova, eds. 467 474. physica, Heidelberg. Ź.
[37] WEFELMEy ER, W. 1994c. Adaptive estimators for parameters of the autoregression function of a Markov chain. Unpublished manuscript. Z.
[38] WELSH, A. H. 1989. On M-processes and M-estimation. Ann. Statist. 17 337 361. Z. · Zbl 0701.62074 · doi:10.1214/aos/1176347021
[39] ZEGER, S. L. and QAQISH, B. 1988. Markov regression models for time series: a quasi-likelihood approach. Biometrics 44 1019 1031. JSTOR: · Zbl 0715.62166 · doi:10.2307/2531732 · links.jstor.org
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.