|
Activity Number:
|
232
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 5, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #302003 |
|
Title:
|
Approximate Inferential Procedures Based on Samples with Nondetects
|
|
Author(s):
|
Avishek Mallick*+ and K. Krishnamoorthy and Thomas Mathew
|
|
Companies:
|
University of Louisiana at Lafayette and University of Louisiana at Lafayette and University of Maryland, Baltimore County
|
|
Address:
|
, Lafayette, LA, 70504,
|
|
Keywords:
|
|
|
Abstract:
|
A generalized variable approach (GV) based on the maximum likelihood estimates for analyzing a sample with nondetects is proposed. The method is applied for the normal case, and is illustrated for constructing prediction limits, one-sided tolerance limits and for setting lower confidence limit for a survival probability. The validity of the methods is evaluated using Monte Carlo simulation. Simulation studies show that the GV approach is satisfactory as long as the proportion of nondetects is not too large. Approximate inferential methods are also given for a gamma distribution. Monte Carlo evaluation of the procedures indicates that the method works satisfactorily for constructing tolerance limits, prediction limits and estimating survival probability for a gamma distribution. The methods are illustrated using some practical examples.
|
- 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 2008 program |
