This talk will discuss mixture based probability density estimation techniques. I will cover methods for the visualization of the time evolution of finite and adaptive mixtures estimators, a method for assessing the underlying complexity of a mixture model based on removal of terms, and several new approaches to the adaptive mixtures density estimation procedure. The talk will provide a retrospective look at my dissertation research along with a little coverage of events since the completion of my dissertation.

This is the first in a series of talks by alumni of the GMU CSI Computational Statistics program. These talks are based on their dissertation research. Jeff Solka along with Wendy Poston holds the distinction of being the first Ph.D. student graduated from the CSI Program. His talk will examine the use of hybrid kernel/mixture estimators in probability density estimation.