|
Activity Number:
|
357
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
General Methodology
|
| Abstract - #300724 |
|
Title:
|
Counting by Weighing
|
|
Author(s):
|
Xinyu Wei *+ and T. Sriram+
|
|
Affiliation(s):
|
Johnson & Johnson Pharmaceutical R&D and University of Georgia
|
|
Address:
|
1125 Trenton-Harbourton Road, Titusville, New Jersey, 08560, US Statistics Building, Athens, Georgia, 30602, U.S.A
|
|
Keywords:
|
sequential sampling ; sample size
|
|
Abstract:
|
We consider the problem of counting a large, but pre-specified, number of items using weight of a small sample. Since weighing items in a small sample saves considerable time and energy, the problem then reduces to that of selecting the size of the sample. Two criteria, one based on estimation and the other based on fixed-width confidence interva,l are used to obtain optimal sample sizes. These sample sizes depend on the unknown coefficient of variation of the weight distribution. To overcome this, sequential sampling schemes are proposed and shown to be as efficient as those available in the literature. Our sampling schemes have an added feature that the sampling operations required are fewer than those available in the literature.
|
- 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 2002 program |
