FRIDAY, February 29, 2008
Time: 1:30 - 2:30 PM
Constant 1048

Title: Mixture Inference at the Edge of Identifiability

Daeyoung Kim
Department of Statistics
The Pennsylvania State University

Identifiability is a principal assumption of statistical models in order to make meaningful inferences. There are two nonidentifiabilities in finite mixture models: boundary nonidentifiability and label nonidentifiability. Although parameters are not identifiable in the strict sense, there is a form of asymptotic identifiability which can provide reasonable answers when components densities are well separated, relative to the sample size. Asymptotic identifiability is related to local identifiability. In this talk, we examine the role of the two key identifiabilities and nonidentifiabilities on finite mixture inference, and investigate estimation and labelling of parameter estimators when the identifiability of the finite mixture model is weak, relative to the sample size. We then propose new methods which can solve several drawbacks of existing methods.