© 2001 by Biometrika Trust
Testing the number of components in a normal mixture
1 Department of Statistics, Harvard University, Cambridge, Massachusetts 02138, U.S.Aytlo{at}hustat.harvard.edu 2 Department of Applied Mathematics and Statistics, State University of New York at Stony Brook, Stony Brook, New York 11794, U.S.A.nmendell{at}notes.cc.sunysb.edu 3 Department of Statistics, Harvard University, Cambridge, Massachusetts 02138, U.S.A. rubin{at}hustat.harvard.edu
We demonstrate that, under a theorem proposed by Vuong, the likelihood ratio statistic based on the KullbackLeibler information criterion of the null hypothesis that a random sample is drawn from a k0-component normal mixture distribution against the alternative hypothesis that the sample is drawn from a k1-component normal mixture distribution is asymptotically distributed as a weighted sum of independent chi-squared random variables with one degree of freedom, under general regularity conditions. We report simulation studies of two cases where we are testing a single normal versus a two-component normal mixture and a two-component normal mixture versus a three-component normal mixture.An empirical adjustment to the likelihood ratio statistic is proposed that appears to improve the rate of convergence to the limiting distribution.
Key Words: KullbackLeibler information criterion; Likelihood ratio test; Normal mixture; Weighted sum of chi-squared random variables
Received April 2000. Revised January 2001
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
N. Ram and K. J. Grimm Methods and Measures: Growth mixture modeling: A method for identifying differences in longitudinal change among unobserved groups International Journal of Behavioral Development, November 1, 2009; 33(6): 565 - 576. [Abstract] [PDF] |
||||
![]() |
H. A. Miller, K. Turner, and C. E. Henderson Psychopathology of Sex Offenders: A Comparison of Males and Females Using Latent Profile Analysis Criminal Justice and Behavior, August 1, 2009; 36(8): 778 - 792. [Abstract] [PDF] |
||||
![]() |
D. M. Dick, S. J. Latendresse, J. E. Lansford, J. P. Budde, A. Goate, K. A. Dodge, G. S. Pettit, and J. E. Bates Role of GABRA2 in Trajectories of Externalizing Behavior Across Development and Evidence of Moderation by Parental Monitoring Arch Gen Psychiatry, June 1, 2009; 66(6): 649 - 657. [Abstract] [Full Text] [PDF] |
||||
![]() |
A. L. Hazen, C. D. Connelly, S. C. Roesch, R. L. Hough, and J. A. Landsverk Child Maltreatment Profiles and Adjustment Problems in High-Risk Adolescents J Interpers Violence, February 1, 2009; 24(2): 361 - 378. [Abstract] [PDF] |
||||
![]() |
R. Dembo, J. Wareham, N. Poythress, K. Meyers, and J. Schmeidler Psychosocial Functioning Problems Over Time Among High-Risk Youths: A Latent Class Transition Analysis Crime Delinquency, October 1, 2008; 54(4): 644 - 670. [Abstract] [PDF] |
||||
![]() |
E. D. Barker, M. Boivin, M. Brendgen, N. Fontaine, L. Arseneault, F. Vitaro, C. Bissonnette, and R. E. Tremblay Predictive Validity and Early Predictors of Peer-Victimization Trajectories in Preschool Arch Gen Psychiatry, October 1, 2008; 65(10): 1185 - 1192. [Abstract] [Full Text] [PDF] |
||||
![]() |
G. W. Smith and M. Shevlin Patterns of Alcohol Consumption and Related Behaviour in Great Britain: A Latent Class Analysis of the Alcohol Use Disorder Identification Test (AUDIT) Alcohol Alcohol., September 1, 2008; 43(5): 590 - 594. [Abstract] [Full Text] [PDF] |
||||
![]() |
K. Turner, H. A. Miller, and C. E. Henderson Latent Profile Analyses of Offense and Personality Characteristics in a Sample of Incarcerated Female Sexual Offenders Criminal Justice and Behavior, July 1, 2008; 35(7): 879 - 894. [Abstract] [PDF] |
||||
![]() |
S. Allua, L. M. Stapleton, and S. N. Beretvas Testing Latent Mean Differences Between Observed and Unobserved Groups Using Multilevel Factor Mixture Models Educational and Psychological Measurement, June 1, 2008; 68(3): 357 - 378. [Abstract] [PDF] |
||||
![]() |
D. E. Bloom and D. Canning Mortality traps and the dynamics of health transitions PNAS, October 9, 2007; 104(41): 16044 - 16049. [Abstract] [Full Text] [PDF] |
||||
![]() |
Mo Wang and T. E. Bodner Growth Mixture Modeling: Identifying and Predicting Unobserved Subpopulations With Longitudinal Data Organizational Research Methods, October 1, 2007; 10(4): 635 - 656. [Abstract] [PDF] |
||||
![]() |
A. D. Steffen, K. Glanz, and L. R. Wilkens Identifying Latent Classes of Adults at Risk for Skin Cancer Based on Constitutional Risk and Sun Protection Behavior Cancer Epidemiol. Biomarkers Prev., July 1, 2007; 16(7): 1422 - 1427. [Abstract] [Full Text] [PDF] |
||||
![]() |
C. L. Odgers, A. Caspi, J. M. Broadbent, N. Dickson, R. J. Hancox, H. Harrington, R. Poulton, M. R. Sears, W. M. Thomson, and T. E. Moffitt Prediction of Differential Adult Health Burden by Conduct Problem Subtypes in Males Arch Gen Psychiatry, April 1, 2007; 64(4): 476 - 484. [Abstract] [Full Text] [PDF] |
||||
![]() |
M. C. Lennon, W. McAllister, L. Kuang, and D. B. Herman Capturing Intervention Effects Over Time: Reanalysis of a Critical Time Intervention for Homeless Mentally Ill Men Am J Public Health, October 1, 2005; 95(10): 1760 - 1766. [Abstract] [Full Text] [PDF] |
||||
![]() |
J. Audrain-McGovern, D. Rodriguez, K. P. Tercyak, J. Cuevas, K. Rodgers, and F. Patterson Identifying and Characterizing Adolescent Smoking Trajectories Cancer Epidemiol. Biomarkers Prev., December 1, 2004; 13(12): 2023 - 2034. [Abstract] [Full Text] [PDF] |
||||
![]() |
G. W. J. M. Stevens, T. V. M. Pels, W. A. M. Vollebergh, and A. A. M. Crijnen Patterns of Psychological Acculturation in Adult and Adolescent Moroccan Immigrants Living in the Netherlands Journal of Cross-Cultural Psychology, November 1, 2004; 35(6): 689 - 704. [Abstract] [PDF] |
||||
![]() |
T. J. Croudace, M.-R. Jarvelin, M. E. J. Wadsworth, and P. B. Jones Developmental Typology of Trajectories to Nighttime Bladder Control: Epidemiologic Application of Longitudinal Latent Class Analysis Am. J. Epidemiol., May 1, 2003; 157(9): 834 - 842. [Abstract] [Full Text] [PDF] |
||||












