next up previous index
Next: biometric.soc.06 Up: Biometric Society (ENAR & Previous: biometric.soc.04

biometric.soc.05


Sponsoring Section/Society: ENAR

Session Slot: 4:00- 5:50 Sunday

Estimated Audience Size: 125-175

AudioVisual Request: Two Overheads


Session Title: Recent Advances in Nonparametric Methods in Biological/Medical Research


Short description about the session: Talks in this session address the recent developed nonparametric methods with application on Biological/Medical Research. Various approaches including kernel, regression spline and additive modeling will be discussed. Each speaker will use one or more examples to illustrate the application of their approaches on biological or medical problems.

Theme Session: No

Applied Session: Yes


Session Organizer: Wang, Naisyin Texas A&M University


Address: Department of Statistics Texas A&M University College Station TX 77843-3143

Phone: 409-845-3141

Fax: ( 409-845-3144

Email: nwang@stat.tamu.edu


Session Timing: 110 minutes total (Sorry about format):

Opening Remarks by Chair - 5 minutes First Speaker - 30 minutes Second Speaker - 30 minutes Third Speaker - 30 minutes Floor Discusion - 5 minutes


Session Chair: Wang, Naisyin Texas A&M University


Address: Department of Statistics Texas A&M University College Station TX 77843-3143

Phone: 409-845-3141

Fax: ( 409-845-3144

Email: nwang@stat.tamu.edu


1. Functional Data Analysis in Aging Research

Wang, Jane-Ling,   University of California, Davis


Address: Division of Statistics University of California, Davis Kerr Hall Davis CA 95616

Phone: 916-752-7624

Fax: 916-752-7099

Email: wnag@wald.ucdavis.edu

Abstract: Due to the soaring size of the elderly population, there is an increasing interest in aging research both from the public and policy point of view and within the scientific communities. The study of the life history of insects plays a central role in experimental aging research. These experiments are often longitudinal studies in which samples of individuals or samples of cohorts are followed over time. The resulting data are a sample of curves (or functionals). For example, in a study of medflies the reproduction history (in terms of the number of eggs laid per day) of 1,000 female medflies was observed. This yields a sample of 1,000 egg laying curves. In another study, the lifetimes of medflies held in 66 cages (with about 6,000 flies per cage) under different treatment were observed. This gives a survival or hazard function for each cohort. A sample of 66 survival functions or 66 hazard functions is thus observed.

When a sample of curves or functionals is observed as in the aforementioned examples, one is then faced with the problem of analyzing a sample of curve data. Such data analysis is termed Functional Data Analysis (FDA) and is often nonparametric in nature. It provides an alternative approach to longitudinal data analysis and has been of keen interest recently to many researchers. Methods for analyzing functional data will be discussed. This will include both existing as well as new procedures. The procedures will be illustrated through several biological applications which arise in aging research.


2. Comparing Nonparametric Models

Bowman, Adrian,   University of Glasgow


Address: Department of Statistics Mathematics Building University Gardens University of Glasgow GLASGOW G12 8QW United Kingdom

Phone: +44-0141-330-4046

Fax: +44-0141-330-4814

Email: adrian@stats.gla.ac.uk

Bock, Mitchum, University of Glasgow

Abstract: Nonparametric models offer attractive extensions to standard linear models because they are able to provide flexible descriptions of non-linear features which often occur in real data. In particular, the general structure of additive models provides a unifying framework for fitting these. Some biometrical examples will be used to illustrate this. However, the tools for comparing models of this type and drawing inferences on covariate effects are not yet so well developed. Some recent work in this area will be described and illustrated.


3. Nonparametric Regression with Measurement Error

Ruppert, David,   Cornell University


Address: School of Operations Research and Industrial Engineering Cornell University Ithaca NY 14853-3801

Phone: 607-255-9136

Fax: 607-255-9129

Email: david@orie.cornell.edu

Carroll, Raymond J., Texas A&M University

Maca, Jeffery D., Cornell University

Abstract: We will describe functional and structural methods for nonparametric regression when the predictor is measured with error. The functional method is the SIMEX estimator of Cook and Stefanski applied to kernel regression: an asymptotic theory is derived. The structural method uses regression splines, with a flexible model for the mismeasured variable.

List of speakers who are nonmembers: None


next up previous index
Next: biometric.soc.06 Up: Biometric Society (ENAR & Previous: biometric.soc.04
David Scott
6/1/1998