| Philosophy | Library |
|
Back to home |
| CompBio | MedStat | ComplexSys | BayesAppl |
Presentations Given Recently.
On-line library.
My general interest is in cross-disciplinary statistical research. I have worked on problems involving numerical weather prediction, polymer mass spectrometry, gene expression microarray experiments, and recently in cellular microscopic imaging and medical imaging. My statistical expertise is broad and I basically like to learn and apply any statistical technqiues which are appropriate for a given problem. I have particularly enjoyed applying nonparametric techniques as well as Bayesian methods, and I have found functional data analysis to be very relevant to many problems in my recent work. Currently I am particularly interested in image analysis techniques and related quantitative measurements. Here is my philosophy about what I do every day and why it is fun to work on interdisciplinary research problems.
In this paper, I develop what it is the precise meaning of "intrinsic dimensionality" associated with analyzing multivariate data, dispelling the scare that is usuallly thrown into high-dimensional modeling in the term "curse of dimensionality". Note that the same theory applies to nonparametric functional data analysis, i.e. regression models in which the covariates take on discretely-sampled measurements of curves in some functional space.