|
Activity Number:
|
93
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 4, 2008 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #301366 |
|
Title:
|
Sequential Unbalanced Ranked Set Sampling
|
|
Author(s):
|
Nader M. Gemayel*+ and Douglas Wolfe and Elizabeth Stasny
|
|
Companies:
|
The Ohio State University and The Ohio State University and The Ohio State University
|
|
Address:
|
404 Cockins Hall, Columbus, OH, 43210,
|
|
Keywords:
|
Sequential methods ; Ranked set sampling ; population proportion
|
|
Abstract:
|
One is often interested in estimating the population proportion of a rare event, where conventional sampling techniques (such as SRS and balanced RSS) are wasteful and inefficient. Moreover, one is also often interested in the units of a population that exceed a certain elevated threshold; for instance, the proportion of fraudulent accounts in a population of accounting records, and the distributional properties of the largest amounts of dollar fraud among the fraudulent accounts. We will explore how sequentially-guided RSS techniques can lead us to target sparsely distributed occurrences of the rare event more accurately.
|
