Conditions For Hyper-EM And Large Graphical Modelling

  • Kim, Seong-Ho (Division of Applied Mathematics, Korea Advanced Institute of Science and Technology) ;
  • Kim, Sung-Ho (Division of Applied Mathematics, Korea Advanced Institute of Science and Technology)
  • Published : 2002.11.01

Abstract

We propose an improved version of Kim (2000) to the effect that in principle we may deal with a graphical model of any size. Kim (2000) proposed a method of estimating parameters for a model of categorical variables which is too large to handle as a single model. We applied the proposed method to a simulated data of 158 binary variables.

Keywords