Assessing the number of components in a normal mixture: an alternative approach

Maciejowska, Katarzyna (2013): Assessing the number of components in a normal mixture: an alternative approach.

Abstract

In this article, a new approach for model specification is proposed. The method allows to choose the correct order of a mixture model by testing, if a particular mixture component is significant. The hypotheses are set in a new way, in order to avoid identification problems, which are typical for mixture models. If some of the parameters are known, the distribution of the LR statistic is Chi2, with the degrees of freedom depending on the number of components and the number of parameters in each component. The advantage of the new approach is its simplicity and computational feasibility.

• Item Type: MPRA Paper
• Language: English
• Keywords: normal mixture models, likelihood ratio test, homogeneity test, hypotheses setting
• Subjects: C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C10 - General; C - Mathematical and Quantitative Methods > C1 - Econometric and Statistical Methods and Methodology: General > C12 - Hypothesis Testing: General

References

Andrews, D. W. K. and W. Ploberger (1994). Optimal tests when a nuisance parameter is present only under the alternative. Econometrica 62 (6), 1383-1414.

Chen, H. and J. Chen (2001). Large sample distribution of the likelihood ratio test for normal mixtures. Statistics & Probability Letters 52, 125-133.

Chen, H. and P. Li (2009). Hypothesis test for normal mixture models: the em approach. The Annals of Statistics 37 (5).

Chen, H., P. Li, and Y. Fu (2012). Inference on the order of a normal mixture. Journal of the American Statistical Association 107 (499), 1096-1105.

Davies, R. B. (1977). Hypothesis testing when a nuisance parameter is present only under the alternative. Biometrika 64 (2), 247-254.

Day, N. E. (1969). Estimating the components of a mixture of normal distributions. Biometrica 56 (3), 463-474.

Dempster, A. P., N. M. Laird, and D. B. Rubin (1977). Maximum-likelihood from incomplete data via the EM algorithm. Journal of Royal Statistics Society Ser. B (methodological) 39, 1-38.

Diebold, F. X. and G. D. Rudebusch (1996). Measuring business cycle: A modern perspective. Review of Economics and Statistics 78, 67-77.

Garel, B. (2001). Likelihood ratio test for univariate gaussian mixture. Journal of Statistical Planning and Inference 96, 325-350.

Garel, B. (2005). Asymptotic theory of the likelihood ratio test for the identification of a mixture. Journal of Statistical Planning and Inference 131, 271-196.

Garel, B. (2007). Recent asymptotic results in testing for mixtures. Computational Statistics & Data Analysis 51, 5295-5304.

Ghosh, J. K. and P. K. Sen (1985). On the asymptotic performance of the log-likelihood ratio statistic for the mixture model and related results. In L. LeCam and R. A. Olshen (Eds.), Proceedings of the Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer, Volume 2, pp. 789{806. Wadsworth, Monteray, CA.

Goodwin, T. H. (1993). Business-cycle analysis with a markov-switching model. Journal of Business & Economic Statistics 11 (3), 331-339.

Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica 57, 357-384.

Hansen, B. E. (1996). Inference when a nuisance parameter is not identified under the null hypothesis. Econometrica 64 (2), 413-430.

Hartigan, J. A. (1985). Statistical theory in clustering. Journal of Classification 2.

Hathaway, R. J. (1985). A constrained formulation of maximum-likelihood estimation for normal mixture distribution. The Annals of Statistics 18 (2), 795-800.

Jedidi, K., H. S. Jagpal, and W. S. Desarbo (1997). Finite mixture structural equation models for response-based segmentation and unobserved heterogeneity. Marketing Science 16, 35-59.

Jeffrues, N. O. (2003). A note on testing the number of components in a normal mixture. Biometrika 90, 991-994.

Kim, C.-J. and C. R. Nelson (1998). Business cycle turning points, a new coincident index, and tests of duration dependence based on a dynamic factor model with regime switching. The Review of Economics and Statistics 80 (2), 188-201.

Kim, C.-J. and C. R. Nelson (1999). Has the U.S. economy become more stable? a bayesian approach based on a markow-switching model of the business cycle. The Review of Economics and Statistics 81 (4), 608-616.

King, M. L. and J. Chen (2010). Testing the order of a finite mixture. Journal of the American Statistical Association 105 (491), 1084-1092.

King, M. L. and T. S. Shively (1993). Locally optimal testing when a nuisance parameter is presented only under the laternative. The Review of Economics and Statistics 75 (1), 1-7.

Lanne, M. (2006). Nonlinear dynamics of interest rate and in ation. Journal of Applied Econometrics 21 (8), 1157-1168.

Liesenfeld, R. (1998). Dynamic bivariate mixture models: modeling the behavior of prices and trading volume. Journal of Business and Economic Statistics 16, 101-109.

Liesenfeld, R. (2001). A generalized bivariate mixture model for stock price volatility and trading volume. Journal of Econometrics 104, 141-178.

Liu, H. and Y. Shao (2004). Asymptotics for the likelihood ratio test in a two-component normal mixture model. Journal of Statistical Planning and Inference 123, 61-81.

Lo, Y., N. R. Mendell, and D. B. Rubin (2001). Testing the number of components in a normal mixture. Biometrika 88 (3), 767-778.

McLachlan, G. J. (1987). On bootstrapping the likelihood ratio test statistic for the number of components in a normal mixture. Applied Statistics 36, 318-324.

McLachlan, G. J. and D. Peel (2000). Finite Mixture Models. New York: Wiley.

Mendell, N. R., H. C. Thode, and S. J. Finch (1991). The likelihood ratio test for the two-component normal mixture problem: Power and sample size analysis. Biometrics 47, 1143-1148.

Perez-Quiros, G. and A. Timmermann (2001). Business cycle asymmetries in stock returns: Evidence from higher order moments and conditional densities. Journal of Econometrics 103, 259-306.

Redner, R. A. and H. F. Walker (1984). Mixture densities, maximum likelihood and the EM algorithm. Society for Industrial and Appied Mathematics 26, 195-239.

Sims, C. A. and T. Zha (2006). Were there regime switches in U.S. monetary policy? American Economic Review 96, 54-81.

SMith, A., P. A. Naik, and C.-L. Tsai (2006). Markov-switching model selection using kullbackleibler divergence. Journal of Econometrics 134, 553-577.

Wolfe, J. H. (1971). A monte carlo study of the sampling distribution of the likelihood ratio for mixtures of multinormal distributions. technical Bulletin STB 72-2, San Diego, US.

Wong, C. S. and W. K. Li (2001). On a logistic mixture autoregressive model. Biometrica 88 (3), 883-846.

Zhang, Z., W. K. Li, and K. C. Yuen (2006). On a mixture garch time-series model. Journal of Time Series Analysis 27 (4), 577-597.