香蕉视频

Title: Regression Models for Spatial Images.

This work is motivated by a problem in describing forest nitrogen cycling, and a consequent goal of constructing regression models for spatial images. Specifically, I present a functional concurrent linear model (FLCM) with varying coefficients for two-dimensional spatial images. To address overparameterization issues, the parameter surfaces in this model are transformed into the wavelet domain and then sparse representations are found using two different methods: LASSO and Bayesian variable selection. I will briefly discuss extensions to address missing data problems for colocated spatial images and the modeling of tree species in landscape ecology. In addition I will discuss the use of the sextant in marine navigation.

Dr. Clayton is a Professor Emeritus in the Departments of Plant Pathology and Statistics at the University of Wisconsin-Madison. His research interests include the development of theoretical statistics as well as the development of statistical tools to address complex problems in the agricultural, environmental and biological sciences. For example, he has focused on the detection and description of patterns of plant and human diseases across large geographical regions. He has applied Bayesian and non-Bayesian methods, coupled with Markov Chain Monte Carlo techniques, to address spatial clustering problems in epidemiology such as identifying locations where the rates of cancer might be enhanced. He has also worked on association studies of variables measured across regions in which there may be spatial correlation. He has collaborated with many scientists on a diverse array of problems, including modeling bee movements to better predict gene flow from transgenic to nontransgenic crops as well as designing clinical trials to compare diets for persons with certain metabolic disorders, to name a few.