|
Activity Number:
|
245
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 8, 2006 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #306910 |
|
Title:
|
Estimating Signatures on a Petition with Cis
|
|
Author(s):
|
Mary M. Whiteside*+ and Mark E. Eakin
|
|
Companies:
|
The University of Texas at Arlington and The University of Texas
|
|
Address:
|
Box 19437, Arlington, TX, 76019,
|
|
Keywords:
|
Goodman ; exact distributions ; replicated signatures
|
|
Abstract:
|
This paper presents a method for constructing a confidence interval estimate of the number of valid, un-replicated, signatures on a petition. The estimation of the number of unique individuals represented by signatures on a petition is one of many important applications of the more general problem of estimating the number of classes in a finite population. The Goodman estimator is widely used for this purpose. We derive critical values from the exact distribution and an unbiased estimator of the variance of the Goodman estimator. Thus, exact confidence intervals can be constructed for the number of unique, valid signatures on a petition.
|
