|
Activity Number:
|
32
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #309574 |
|
Title:
|
Weibull Prediction Limits with Retesting
|
|
Author(s):
|
Kirk Cameron*+
|
|
Companies:
|
MacStat Consulting, Ltd
|
|
Address:
|
10330 Mill Creek Ct, Colorado Springs, CO, 80908,
|
|
Keywords:
|
Weibull distribution ; prediction limits ; retesting ; groundwater ; monitoring
|
|
Abstract:
|
EPA guidance for groundwater monitoring recommends simultaneous prediction limits combined with retesting. Under this rubric, an initial exceedance of the background prediction limit among measurements from a set of monitoring wells is followed by a confirmatory test at each exceeding well. This allows control of nominal site-wide false positive rates (SWFPPR) while ensuring power to detect contaminated groundwater. Past research has led to solutions for normal-, lognormal-, and gamma-based limits, as well as non-parametric limits. We extend that work to simultaneous two-parameter Weibull prediction limits, illustrating the theory and providing methods for practical computation. We also compare Weibull limits against other parametric and nonparametric limits in real samples of groundwater data. The Weibull distribution acquits itself as a flexible tool in groundwater monitoring.
|
- 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 2007 program |
