Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Initial Value Selection in Applying an EM Algorithm for Recursive Models of Categorical Variables

  • Jeong, Mi-Sook (Department of Statistics, Pusan National University, Pusan 609-735, South Korea) ;
  • Kim, Sung-Ho (Basic Sciences Division, Korea Advanced Institute of Science and Technolog, Taejon 305-701) ;
  • Jeong, Kwang-Mo (Research Institute of Information and Communication, Department of Statistics, Pusan National University, Pusan 609-735, South Korea)
  • Published : 1998.03.01
Download PDF
⟨ Previous Next ⟩

Abstract

Maximum likelihood estimates (MLEs) for recursive models of categorical variables are discussed under an EM framework. Since MLEs by EM often depend on the choice of the initial values for MLEs, we explore reasonable rules for selecting the initial values for EM. Simulation results strongly support the proposed rules.

Keywords

References

  1. Categorical Data Analysis Agresti, A.
  2. Los Angeles: BMDP Statistical Software. Theory and Implementation of EQS: A Structural Equations Program Bentler, P.M.
  3. Discrete Multivariate Analysis: Theory and Practice(Sixth printing) Bishop, Y.M.;Fienberg, S.E.;Holland, P.W.
  4. Structural Equations with Latent Variables Bollen, K.A.
  5. Journal of the Royal Statistical Society v.B no.39 Maximum like-lihood from incomplete data via the EM algorithm(with discussion) Dempster, A.P.;Laird, N.M.;Rubin, D.B.
  6. The Annals of Statistics v.6 no.2 The geometry exponential families Efron, B.
  7. The Analysis of Cross-Classified Categorical Data(2nd ed.) Fienberg, S. E.
  8. Proc. Cambridge Philos. Trans. v.122 Theory of statistical estimation Fisher, R. A.
  9. Stevens' handbook of experimental psychology(2nd ed.) v.Ⅱ Problem Solving and Reasoning Greeno, J.G.;Simon, H.A.;R.C. Atkinson(ed.);R.J. Herrnstein(ed.);G. Lindzey(ed.);R.D. Luce(ed.)
  10. LISREL Ⅵ: Analysis of Linear Structural Relationships by Maximum Likelihood and Least Squares Method Joreskog, K.G.;Sorbom D.
  11. Korean Educational Evaluation Research v.7 no.2 An Approach to Statistical Modelling for Task Ability and Task Performance(in Korean) Kim S.- H.
  12. Communications in Statistics v.26 no.6 Iterative Proportional Fitting for Nonhierarchical Loglinear Models Kim S.- H.
  13. Comp. Stat. & Data Anal. v.19 The EM Algorithm for graphical association models with missing Data Lauritzen, S.L.
  14. Biometrika v.70 no.3 Graphical and Recursive Models for Contingency Tables Lauritzen, S. L.;Wermuth, N.
  15. Influence Diagrams, Belief Nets and Decision Analysis(edition) Oilver, R.M.;Smith J.Q.
  16. Probabilistic Reasoning in Intelligent Systems: Notworks of Plausible Inference Pearl, J.
  17. Linear Statistical Inference and Its Applications.(2nd ed.) Rao, C.R.
  18. Journal of Computational and Graphical Statistics v.6 no.2 On the ordering and groupings of conditional maximizations within ECM-type Algorithms Van Dyk, D;Meng, X.L.
  19. Graphical Models in Applied Multivariate Statistics Whittaker, J.
  20. The Annals of Statistics v.11 no.1 On the convergence properties of the EM algorithm Wu, C.F.