×

Maximum likelihood estimation of multinomial probit factor analysis models for multivariate \(t\)-distribution. (English) Zbl 1306.65073

Summary: We propose a model for multinomial probit factor analysis by assuming \(t\)-distribution error in probit factor analysis. To obtain maximum likelihood estimation, we use the Monte Carlo expectation maximization algorithm with its M-step greatly simplified under conditional maximization and its E-step made feasible by Monte Carlo simulation. Standard errors are calculated by using Louis’s method. The methodology is illustrated with numerical simulations.

MSC:

62-08 Computational methods for problems pertaining to statistics
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Albert JH, Chib S (1993) Bayesian analysis of polychotomous response data. J Am Stat Assoc 88:669-679 · Zbl 0774.62031 · doi:10.1080/01621459.1993.10476321
[2] Ashford JR, Sowden RR (1970) Multi-variate probit analysis. Biometrics 26:535-546 · doi:10.2307/2529107
[3] Carnahan B, Luther HA, Wilkes JO (1969) Applied numerical methods. Wiley, New York · Zbl 0195.44701
[4] Chan JSK, Kuk AYC (1997) Maximum likelihood estimation for probit-linear mixed models with correlated random effects. Biometrics 53:86-97 · Zbl 1065.62503 · doi:10.2307/2533099
[5] Daganzo C (1980) Multinomial probit. Academic, New York
[6] Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood estimation from incomplete observations. J R Stat Soc B 39:1-38 · Zbl 0364.62022
[7] Diebolt, J.; Ip, EHS; Gilks, WR (ed.); Richardson, S. (ed.); Speigelhalter, DJ (ed.), Stochastic EM: method and application (1998), New York
[8] Fraser DAS (1979) Inference and linear models. McGraw-Hill, New York · Zbl 0455.62052
[9] Geman S, Geman D (1984) Stochastic relaxation, Gibbs distribution, and the Bayesian restoration of image. IEEE Trans Pattern Anal Mach Intell 6:721-741 · Zbl 0573.62030 · doi:10.1109/TPAMI.1984.4767596
[10] Hausman J, Wise D (1978) A conditional probit model for qualitative choice: discrete decisions recognizing interdependence and heterogeneous preferences. Econometrica 45:319-339 · Zbl 0376.90005
[11] Hartley H (1958) Maximum likelihood estimation from incomplete data. Biometrics 14:179-194 · Zbl 0081.13904 · doi:10.2307/2527783
[12] Jeffreys H (1939) Theory of probability. Clarendon Press, Oxford · JFM 65.0546.04
[13] Lange K, Little RJA, Taylor JMG (1989) Robust statistical modeling using the t-distribution. J Am Stat Assoc 84:881-896
[14] Lerman S, Manski C (1981) On the use of simulated frequencies to approximate choice probabilities. In: Manski C, McFadden D (eds) Structural analysis of discrete data with econometric applications. MIT Press, Cambridge, pp 305-319 · Zbl 0850.62890
[15] Little RJA (1988) Robust estimation of the mean and covarianve matrix from data with missing values. Appl Stat 37:23-39 · Zbl 0647.62040 · doi:10.2307/2347491
[16] Liu C (1995) Missing data imputation using the multivariate t distribution. J Multivar Anal 53:139-158 · Zbl 0855.62051 · doi:10.1006/jmva.1995.1029
[17] Liu C (1997) ML estimation of the multivariate t distribution and the EM algorithm. J Multivar Anal 63:296-312 · Zbl 0884.62059 · doi:10.1006/jmva.1997.1703
[18] Liu C, Rubin DB (1995) ML estimation of the t distribution using EM and its extensions, ECM and ECME. Stat Sin 5:19-39 · Zbl 0824.62047
[19] Louis TA (1982) Finding the observed information matrix when using the EM algorithm. J R Stat Soc B 44:226-233 · Zbl 0488.62018
[20] Maronna RA (1976) Robust M-estimators of multivariate location and scatter. Ann Stat 4:51-67 · Zbl 0322.62054 · doi:10.1214/aos/1176343347
[21] McCulloch CE (1994) Maximum likelihood variance components estimation for binary data. J Am Stat Assoc 89:330-335 · Zbl 0800.62139 · doi:10.1080/01621459.1994.10476474
[22] McCulloch R, Rossi PE (1994) An exact likelihood analysis of the multinomial probit model. J Econom 64:207-240 · doi:10.1016/0304-4076(94)90064-7
[23] McFadden D (1989) A method of simulated moments for estimation of discrete response models without numerical integration. Econometrica 57:995-1027 · Zbl 0679.62101 · doi:10.2307/1913621
[24] McLachlan GJ, Peel D (1998) Robust cluster analysis via mixtures of multivariate t-distributions. In: Amin A, Dori D, Pudil P, Freeman H (eds) Lecture notes in computer science, vol 1451. Springer, Berlin · Zbl 0573.62030
[25] McLachlan GJ, Bean RW (2007) Extension of the mixture of factor analyzers model to incorporate the multivariate t-distribution. Comput Stat Data Anal 51:5327-5338 · Zbl 1445.62053 · doi:10.1016/j.csda.2006.09.015
[26] Meng X, Rubin DB (1993) Maximum likelihood estimation via the ECM algorithm: a general framework. Biometrika 80:267-278 · Zbl 0778.62022 · doi:10.1093/biomet/80.2.267
[27] Meng X, Schilling S (1996) Fitting full-information item factor models and an empirical investigation of bridge sampling. J Am Stat Assoc 91:1254-1267 · Zbl 0925.62220 · doi:10.1080/01621459.1996.10476995
[28] Natarajan R, McCulloch CE, Kiefer NM (2000) A Monte Carlo EM method for estimating multinomial probit models. Comput Stat Data Anal 34:33-50 · Zbl 1052.62508 · doi:10.1016/S0167-9473(99)00073-0
[29] Pinheiro JC, Liu C, Wu Y (2001) Efficient algorithms for robust estimationin linear mixed-effects models using the multivariate t distribution. J Comput Graph Stat 10:249-276 · doi:10.1198/10618600152628059
[30] Rubin DB (1983) Iteratively reweighted least squares. In: Encyclopedia of the statistical sciences. Wiley, New York
[31] Rocke DM, Woodruff DL (1997) Robust estimation of multivariate location and shape. J Stat Plan Inference 57:245-255 · Zbl 0900.62281 · doi:10.1016/S0378-3758(96)00047-X
[32] Shoham S (2002) Robust clustering by deterministic agglomeration EM of mixtures of multivariate t-distribution. Pattern Recognit 35:1127-1142 · Zbl 1005.68051
[33] Song XY, Lee SY (2005) A multivariate probit latent variable model for analyzing dichotomous responses. Stat Sin 15:645-664 · Zbl 1086.62074
[34] Stern S (1992) A method for smoothing simulated moments of discrete probabilities in multinomial probit models. Econometrica 60:943-952 · Zbl 0850.62890 · doi:10.2307/2951573
[35] Sutradhar BC, Ali MM (1986) Estimation of the parameters of a regression model with a multivariate t error variable. Commun Stat Theory Methods 15:429-450 · Zbl 0608.62061
[36] Wei GCG, Tanner MA (1990) A Monte Carlo implementation of the EM algorithm and the poor man’s data augmentation algorithm. J Am Stat Assoc 85:699-704 · doi:10.1080/01621459.1990.10474930
[37] Zhao J, Jiang Q (2006) Probabilistic PCA for t distributions. Neurocomputing 69:2217-2226 · doi:10.1016/j.neucom.2005.07.011
[38] Zhou X, Liu X (2008) The Monte Carlo EM method for estimating multinomial probit latent variable models. Comput Stat 80:267-278
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.