Gongjun Xu ColloquiumThursday, August 27, 2015 - 2:45pm
Statistics Department Colloquium
Where: Close-Hipp Building, Room 364
Speaker: Gongjun Xu
Affiliation: University of Minnesota, Department of Statistics
Title: Identifiability of Restricted Latent Class Models with Binary Responses
Abstract: Statistical latent class models are widely used in social and psychological researches, yet it is often difficult to establish the identifiability of the model parameters. In this talk we consider the identifiability issue of a family of restricted latent class models, where the restriction structures are pre-specified to reflect assumptions on the related assessment. We establish the identifiability results in the strict sense and specify which types of restriction structures would give the identifiability of the model parameters. The results not only ensure the validity of many of the popularly used models, but also provide a guideline for the related experimental design. Theoretically, we develop a new technique to establish the identifiability result, which is different from the existing methods and may be extended to other restricted latent class models.