U.S. Department of Energy

Pacific Northwest National Laboratory

Gaussian Processes in the Study of Cognition

Tuesday, July 26, 2016
Joseph Houpt
Assistant Professor
Wright State University
Many empirical studies of cognition focus on comparing estimates of single points (e.g., mean response times, choice probabilities, test scores). This is due, at least in part, to constraints imposed by using traditional statistical analyses such as t-tests, ANOVAs and regression. Even in areas in which multidimensional dependent variables are used, analysis is usually confined to relatively small dimensional vectors. In this talk I will give an overview of various tools applications of functional data analysis in my research. I will discuss applications in the analysis of response time distributions, a major focus of my work thus far, as well as more recent work on eye-tracking and motor control.
Speaker Bio

Joseph W. Houpt is an Assistant Professor at Wright State University in Dayton, Ohio. He received a Bachelor’s in Mathematics from the University of Utah, a Master’s in Artificial Intelligence from the University of Edinburgh, and a Ph.D. in Psychology and Cognitive Science from Indiana University. He has authored 19 peer reviewed journal articles, including two of the top 25 most cited articled in the Journal of Mathematical Psychology, many book chapters and conference papers, and co-edited a recently published two-volume set on mathematical models of cognition and perception. 

| Pacific Northwest National Laboratory