The impact of covariance misspecification in multivariate Gaussian mixtures on estimation and inference: An application to longitudinal modeling

Statistics in Medicine

Volumn 32, Issue 16, 2013, Pages 2790-2803

  Heggeseth, Brianna C ^a   Jewell, Nicholas P ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

Covariance; Kullback Leibler divergence; Mixture models; Model misspecification

Indexed keywords

ADOLESCENT; ADULT; ANALYTICAL ERROR; ARTICLE; BODY MASS; CONTROLLED STUDY; CORRELATION ANALYSIS; FEMALE; HUMAN; LONGITUDINAL STUDY; MALE; MATHEMATICAL MODEL; MATHEMATICAL PARAMETERS; MAXIMUM LIKELIHOOD METHOD; MULTIVARIATE ANALYSIS OF COVARIANCE; MULTIVARIATE GAUSSIAN MIXTURE; NORMAL DISTRIBUTION; PROBABILITY; REGRESSION ANALYSIS;

ADOLESCENT; BODY MASS INDEX; COMPUTER SIMULATION; FEMALE; HUMANS; LIKELIHOOD FUNCTIONS; LONGITUDINAL STUDIES; MALE; MODELS, STATISTICAL; MULTIVARIATE ANALYSIS; YOUNG ADULT;

EID: 84879142467     PISSN: 02776715     EISSN: 10970258     Source Type: Journal    
DOI: 10.1002/sim.5729     Document Type: Article

References (47)

1. Everitt B, Hand D. Finite Mixture Distributions. Chapman & Hall: London, 1981.
2. Titterington DM, Smith AFM, Makov UE. Statistical Analysis of Finite Mixture Distributions, Wiley Series in Probability and Statistics. Wiley: New York, 1985.
3. McLachlan GJ, Basford KE. Mixture Models: Inference and Applications to Clustering. Marcel Dekker: New York/Basel, 1988.
4. McLachlan GJ, Peel D. Finite Mixture Models, Wiley Series in Probability and Statistics. Wiley: New York, 2000.
5. Frühwirth-Schnatter S. Finite Mixture and Markov Switching Models. Springer: New York, 2006.
6. Dela Cruz-Mesía R, Quintana FA, Marshall G. Model-based clustering for longitudinal data. Computational Statistics & Data Analysis 2008; 52:1441-1457. DOI: 10.1016/j.csda.2007.04.005.
7. Wedel M. Concomitant variables in finite mixture models. Statistica Neerlandica 2002; 56(3):362-375. DOI: 10.1111/1467-9574.t01-1-00072.
8. Schlattmann P. Medical applications of finite mixture models. International Statistical Review 2011; 79(2):294-294. DOI: 10.1111/j.1751-5823.2011.00149 20.x.
9. Nagin D. Analyzing developmental trajectories: a semiparametric, group-based approach. Psychological Methods 1999; 4(2):139-157. DOI: 10.1037/1082-989X.4.2.139.
10. Nagin D. Group-based Modeling of Development. Harvard University Press: Cambridge, 2005.
11. Muthén B, Muthén L. Integrating person-centered and variable-centered analyses: growth mixture modeling with latent trajectory classes. Alcoholism: Clinical and Experimental Research 2000; 24(6):882-891. DOI: 10.1111/j.1530-0277.2000.tb02070.x.
12. Muthén B. Second-generation structural equation modeling with a combination of categorical and continuous latent variables: new opportunities for latent class-latent growth modeling. In New Methods for the Analysis of Change, Collins L, Sayers A (eds). American Psychological Association: Washington, D.C., 2001; 291-322, DOI: 10.1037/10409-010.
13. Pickles A, Croudace T. Latent mixture models for multivariate and longitudinal outcomes. Statistical Methods in Medical Research 2010; 19(3):271-289. DOI: 10.1177/0962280209105016.
14. Jones B, Nagin D, Roeder K. A SAS procedure based on mixture models for estimating developmental trajectories. Sociological Methods & Research 2001; 29(3):374.
15. Leisch F. FlexMix: a general framework for finite mixture models and latent class regression in R. Journal of Statistical Software 2004; 11(8):1-18.
16. Fraley C, Raftery A. Mclust: software for model-based cluster analysis. Journal of Classification 1999; 16(2):297-306.
17. Muthén L, Muthén B. Mplus User's Guide, (7th edn). Muthén & Muthén: Los Angeles, 1998-2012.
18. Vermunt J, Magidson J. Latent Gold 4.0 User's Guide. Statistical Innovations Inc.: Belmont, 2005.
19. Oliveira-Brochado A, Martins FV. Assessing the number of components in mixture models: a review. FEP Working Papers 194, Universidade do Porto, Faculdade de Economia do Porto, 2005.
20. Gray G. Bias in misspecified mixtures. Biometrics 1994; 50(2):457-470.
21. Lo Y. Bias from misspecification of the component variances in a normal mixture. Computational Statistics & Data Analysis 2011; 55:2739-2747. DOI: 10.1016/j.csda.2011.04.007.
22. Banfield JD, Raftery AE. Model-based Gaussian and non-Gaussian clustering. Biometrics 1993; 49(3):803-821.
23. McNicholas PD, Murphy TB. Model-based clustering of longitudinal data. Canadian Journal of Statistics 2010; 38(1):153-168. DOI: 10.1002/cjs.10047.
24. Muthén B, Shedden K. Finite mixture modeling with mixture outcomes using the EM algorithm. Biometrics 1999; 55(2):463-469. DOI: 10.1111/j.0006-341X.1999.00463.x.
25. Ostbye T, Malhotra R, Landerman LR. Body mass trajectories through adulthood: results from the National Longitudinal Survey of Youth 1979 cohort (1981-2006). International Journal of Epidemiology 2011; 40(1):240-250. DOI: 10.1093/ije/dyq142.
26. Muthén B, Brown H, Leuchter A, Hunter A. General approaches to analysis of course: applying growth mixture modeling to randomized trials of depression medication. In Causality and Psychopathology: Finding the Determinants of Disorders and their Cures, Shrout P, Keyes K, Ornstein K (eds). Oxford University Press: New York, 2008; 159-178.
27. Liang K-Y, Zeger SL. Longitudinal data analysis using generalized linear models. Biometrika 1986; 73(1):13-22. DOI: 10.1093/biomet/73.1.13.
28. White H. Maximum likelihood estimation of misspecified models. Econometrica 1982; 50(1):1-25.
29. Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B (Methodological) 1977; 39(1):1-38.
30. Teicher H. Identifiability of finite mixtures. The Annals of Mathematical Statistics 1963; 34(4):1265-1269. DOI: 10.1214/aoms/1177703862.
31. Yakowitz S, Spragins J. On the identifiability of finite mixtures. The Annals of Mathematical Statistics 1968; 39(1):209-214. DOI: 10.1214/aoms/1177698520.
32. Hennig C. Identifiablity of models for clusterwise linear regression. Journal of Classification 2000; 17(2):273-296. DOI: 10.1007/s003570000022.
33. Jiang W, Tanner M. On the identifiability of mixtures-of-experts. Neural Networks 1999; 12(9):1253-1258. DOI: 10.1016/S0893-6080(99)00066-0.
34. Day N. Estimating the components of a mixture of normal distributions. Biometrika 1969; 56(3):463-474. DOI: 10.1093/biomet/56.3.463.
35. Kiefer J, Wolfowitz J. Consistency of the maximum likelihood estimator in the presence of infinitely many incidental parameters. The Annals of Mathematical Statistics 1956; 27(4):887-906. DOI: 10.1214/aoms/1177728066.
36. Kiefer N. Discrete parameter variation: efficient estimation of a switching regression model. Econometrica 1978; 46:427-434.
37. Hathaway R. A constrained formulation of maximum-likelihood estimation for normal mixture distributions. The Annals of Statistics 1985; 13(2):795-800. DOI: 10.1214/aos/1176349557.
38. Wald A. Note on the consistency of the maximum likelihood estimate. The Annals of Mathematical Statistics 1949; 20(4):595-601. DOI: 10.1214/aoms/1177729952.
39. LeCam L. On some asymptotic properties of maximum likelihood estimates and related bayes estimates. Univeristy of California Publications in Statistics 1953; 1:277-330.
40. Jennrich R. Asymptotic properties of non-linear least squares estimators. The Annals of Mathematical Statistics 1969; 40(2):633-643. DOI: 10.1214/aoms/1177697731.
41. Boldea O, Magnus J. Maximum likelihood estimation of the multivariate normal mixture model. Journal of the American Statistical Association 2009; 104(488):1539-1549. DOI: 10.1198/jasa.2009.tm08273.
42. Dasgupta S.Learning mixtures of Gaussians. In Proceedings of the IEEE Symposium on Foundations of Computer Science, New York, 1999; 634-644.
43. Shults J, Sun W, Tu X, Kim H, Amsterdam J, Hilbe JM, Ten-Have T. A comparison of several approaches for choosing between working correlation structures in generalized estimating equation analysis of longitudinal binary data. Statistics in Medicine 2009; 28(18):2338-2355. DOI: 10.1002/sim.3622.
44. Rotnitzky A, Jewell N. Hypothesis testing of regression parameters in semiparametric generalized linear models for cluster correlated data. Biometrika 1990; 77(3):485-497. DOI: 10.1093/biomet/77.3.485.
45. Grün B, Leisch F. Bootstrapping finite mixture models. In Compstat 2004-Proceeding in Computational Statistics, Antoch J (ed.). Physica Verlag: Heidelberg, Germany, 2004; 1115-1122.
46. Diggle P, Liang K, Zeger S. Analysis of Longitudinal Data, (2nd edn). Oxford University Press: USA, 2002.
47. Wang C, Brown C, Bandeen-Roche K. Residual diagnostics for growth mixture models. Journal of the American Statistical Association 2005; 100(471):1054-1076. DOI: 10.1198/016214505000000501.