|
Activity Number:
|
309
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Memorial
|
| Abstract - #305274 |
|
Title:
|
Signals and Noises: Statistical Models Based on Fundamental Tenets of the Environmental and Ecological Sciences
|
|
Author(s):
|
Mark S. Kaiser*+
|
|
Companies:
|
Iowa State University
|
|
Address:
|
Department of Statistics, Ames, IA, 50011-0001,
|
|
Keywords:
|
mixture models ; dynamic models ; law of limiting factors ; maximum likelihood ; Bayesian analysis
|
|
Abstract:
|
Environmental and ecological scientists often indicate that data they obtain in field studies is exceedingly "noisy." This suggests a conceptualization of the problems under investigation as "signal" plus "noise," a familiar structure for statistical models with additive errors. But most environmental and ecological process actually consist of a number of "signals" and a number of "noises." A profitable approach to the formulation of statistical models for any number of problems in these areas is to use the basic ecological theory involved to define the primary "signal" of concern. This can lead to interesting statistical structures, as is illustrated with several problems that have arisen through interactions with applied ecologists and environmental scientists.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2006 program |
