297311
Clustering incomplete data via normal mixture models and multiple imputation
Clustering incomplete data via normal mixture models and multiple imputation
Tuesday, November 18, 2014
: 4:50 PM - 5:10 PM
Clustering with normal mixture models describes groups in a dataset using normal distributions. However, existing methods require complete data. Multiple imputation, a simulation-based approach to incomplete data, does not combine in a straightforward manner with clustering. We have developed a new method to cluster incomplete data using multiple imputation. We illustrate how our new method outperforms complete-case methodology with a simulation study, then demonstrate the utility of the method in a data application.
Learning Areas:
Biostatistics, economicsLearning Objectives:
Describe clusters in incomplete data using normal mixture models.
Presenting author's disclosure statement:
Qualified on the content I am responsible for because: I am a fourth year Ph.D. student at the University of Connecticut, working on a thesis which includes the clustering of incomplete data. Among my research interests are clustering and multiple imputation.
Any relevant financial relationships? No
I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.