[Previous] | [Session 60] | [Next]
L. Wasserman (Carnegie Mellon)
Nonparametric statistical methods allow one to analyze data without making strong assumptions about the process that generated the data. For example, instead of assuming that the data have a Gaussian distribution, we might assume only that the distribution has a probability density that satisfies some weak, smoothness conditions. I will discuss three methods for estimating probability density functions: mixture models, kernel density estimation and wavelets. Finally, I will illustrate these methods applied to Astrophysics data. These applications are based on a collaboration between Astrophysicists (Andy Connolly, Bob Nichol), Computer Scientists (Andrew Moore, Jeff Schneider) and Statisticians (Chris Genovese and me).
The author(s) of this abstract have provided an email address for comments about the abstract: larry@stat.cmu.edu