Maximum Likelihood Estimation in Latent Class Models for Contingency Table Data
Yi Zhou, MLD, CMU

Abstract

Statistical models with latent structure have a history going back to the 1950s and have seen widespread use in the social sciences and, more recently, in computational biology and in machine learning. In this talk, I will talk about the basic latent class model proposed originally by the sociologist Paul F. Lazarfeld for categorical data, and I will explain its geometric structure. I will draw parallels between the statistical and geometric properties of latent class models and illustrate geometrically the causes of many problems associated with maximum likelihood estimation and related statistical inference. In particular, I will focus on issues of non-identifiability and determination of the model dimension, of maximization of the likelihood function and on the effect of symmetric data. I will illustrate these phenomena with both synthetic and real-life tables, of different dimension and complexity.

Bio

Venue, Date, and Time

Venue: NSH 1507

Date: Monday, December 10

Time: 12:00 noon

Slides