Display options
Cite
Teel C, Park T, Sampson AR. EM Estimation for Finite Mixture Models with Known Mixture Component Size. Commun Stat Simul Comput. 2015;44(6):1545-1556doi: 10.1080/03610918.2013.824091.
Teel, C., Park, T., & Sampson, A. R. (2015). EM Estimation for Finite Mixture Models with Known Mixture Component Size. Communications in statistics: Simulation and computation, 44(6), 1545-1556. https://doi.org/10.1080/03610918.2013.824091
Teel, Chen, et al. "EM Estimation for Finite Mixture Models with Known Mixture Component Size." Communications in statistics: Simulation and computation vol. 44,6 (2015): 1545-1556. doi: https://doi.org/10.1080/03610918.2013.824091
Teel C, Park T, Sampson AR. EM Estimation for Finite Mixture Models with Known Mixture Component Size. Commun Stat Simul Comput. 2015 Jul;44(6):1545-1556. doi: 10.1080/03610918.2013.824091. PMID: 25663737; PMCID: PMC4314727.
Copy Download .nbib Format: NLM
Share it on

Commun Stat Simul Comput. 2015 Jul;44(6):1545-1556. doi: 10.1080/03610918.2013.824091.

EM Estimation for Finite Mixture Models with Known Mixture Component Size.

Communications in statistics: Simulation and computation

Chen Teel, Taeyoung Park, Allan R Sampson

Affiliations

  1. Applied Statistics Group, E. I. du Pont de Nemours & Company, DE, USA.
  2. Department of Applied Statistics, Yonsei University, Seoul, Korea.
  3. Department of Statistics, University of Pittsburgh, PA, USA.

PMID: 25663737 PMCID: PMC4314727 DOI: 10.1080/03610918.2013.824091

Abstract

We consider the use of an EM algorithm for fitting finite mixture models when mixture component size is known. This situation can occur in a number of settings, where individual membership is unknown but aggregate membership is known. When the mixture component size, i.e., the aggregate mixture component membership, is known, it is common practice to treat only the mixing probability as known. This approach does not, however, entirely account for the fact that the number of observations within each mixture component is known, which may result in artificially incorrect estimates of parameters. By fully capitalizing on the available information, the proposed EM algorithm shows robustness to the choice of starting values and exhibits numerically stable convergence properties.

Keywords: Aggregate data; Conditional Bernoulli distribution; EM algorithm; Finite mixture models

References

  1. Stat Med. 2002 Jan 30;21(2):165-76 - PubMed
  2. Biometrics. 2008 Jun;64(2):424-30 - PubMed
  3. Stat Med. 2005 Jun 30;24(12):1807-14 - PubMed
  4. Stat Med. 1999 Dec 30;18(24):3493-509 - PubMed
  5. Stat Med. 2001 Dec 30;20(24):3861-73 - PubMed

Publication Types

Grant support