Inference for mixtures of symmetric distributions. (English) Zbl 1114.62035

Hunter, David R.; Wang, Shaoli; Hettmansperger, Thomas P.

Ann. Stat. 35, No. 1, 224-251 (2007).

Summary: This article discusses the problem of estimation of parameters in finite mixtures when the mixture components are assumed to be symmetric and to come from the same location family. We refer to these mixtures as semi-parametric because no additional assumptions other than symmetry are made regarding the parametric form of the component distributions. Because the class of symmetric distributions is so broad, identifiability of parameters is a major issue in these mixtures.
We develop a notion of identifiability of finite mixture models, which we call \(k\)-identifiability, where \(k\) denotes the number of components in the mixture. We give sufficient conditions for \(k\)-identifiability of location mixtures of symmetric components when \(k=2\) or 3. We propose a novel distance-based method for estimating the (location and mixing) parameters from a \(k\)-identifiable model and establish the strong consistency and asymptotic normality of the estimator.
In the specific case of \(L_2\)-distance, we show that our estimator generalizes the Hodges-Lehmann estimator. We discuss the numerical implementation of these procedures, along with an empirical estimate of the component distribution, in the two-component case. In comparisons with maximum likelihood estimation assuming normal components, our method produces somewhat higher standard error estimates in the case where the components are truly normal, but dramatically outperforms the normal method when the components are heavy-tailed.

MSC:

62G05	Nonparametric estimation
62F12	Asymptotic properties of parametric estimators
62G20	Asymptotic properties of nonparametric inference

Keywords:

deconvolution; Hodges-Lehmann estimator; identifiability; semi-parametric mixtures

References:

[1]	Arcones, M. A., Chen, Z. and Giné, E. (1994). Estimators related to \(U\)-processes with applications to multivariate medians: Asymptotic normality. Ann. Statist. 22 1460–1477. · Zbl 0827.62023 · doi:10.1214/aos/1176325637
[2]	Billingsley, P. (1986). Probability and Measure , 2nd ed. Wiley, New York. · Zbl 0649.60001
[3]	Bordes, L., Mottelet, S. and Vandekerkhove, P. (2006). Semiparametric estimation of,a,two-component,mixture,model. Ann.,Statist. 34 1204–1232. · Zbl 1112.62029 · doi:10.1214/009053606000000353
[4]	Cruz-Medina, I. R. and Hettmansperger, T. P. (2004). Nonparametric estimation in semi-parametric univariate mixture models. J. Stat. Comput. Simul. 74 513–524. · Zbl 1060.62041 · doi:10.1080/00949650310001602158
[5]	Ellis, S. P. (2002). Blind deconvolution when noise is symmetric: Existence and examples of solutions. Ann. Inst. Statist. Math. 54 758–767. · Zbl 1047.62049 · doi:10.1023/A:1022459217720
[6]	Hall, P. and Zhou, X.-H. (2003). Nonparametric estimation of component distributions in a multivariate mixture. Ann. Statist. 31 201–224. · Zbl 1018.62021 · doi:10.1214/aos/1046294462
[7]	Hettmansperger, T. P. and Thomas, H. (2000). Almost nonparametric inference for repeated measures in mixture models. J. R. Stat. Soc. Ser. B Stat. Methodol. 62 811–825. JSTOR: · Zbl 0957.62026 · doi:10.1111/1467-9868.00266
[8]	Hodges, J. L., Jr. and Lehmann, E. L. (1963). Estimates of location based on rank tests. Ann. Math. Statist. 34 598–611. · Zbl 0203.21105 · doi:10.1214/aoms/1177704172
[9]	Lee, A. J. (1990). \(U\)- Statistics: Theory and Practice . Dekker, New York. · Zbl 0771.62001
[10]	Lindsay, B. G. (1995). Mixture Models: Theory, Geometry and Applications . IMS, Hayward, CA. · Zbl 1163.62326
[11]	McLachlan, G. and Peel, D. A. (2000). Finite Mixture Models . Wiley, New York. · Zbl 0963.62061
[12]	Pollard, D. (1985). New ways to prove central limit theorems. Econometric Theory 1 295–314.
[13]	Titterington, D. M., Smith, A. F. M. and Makov, U. E. (1985). Statistical Analysis of Finite Mixture Distributions . Wiley, Chichester. · Zbl 0646.62013
[14]	Walther, G. (2001). Multiscale maximum likelihood analysis of a semiparametric model, with applications. Ann. Statist. 29 1297–1319. · Zbl 1043.62043 · doi:10.1214/aos/1013203455
[15]	Walther, G. (2002). Detecting the presence of mixing with multiscale maximum likelihood. J. Amer. Statist. Assoc. 97 508–513. JSTOR: · Zbl 1073.62533 · doi:10.1198/016214502760047032
[16]	Yakowitz, S. J. and Spragins, J. D. (1968). On the identifiability of finite mixtures. Ann. Math. Statist. 39 209–214. · Zbl 0155.25703 · doi:10.1214/aoms/1177698520