|
Activity Number:
|
36
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #308420 |
|
Title:
|
Optimal 2-Stage Sampling Theory for Business Customer Satisfaction Surveys
|
|
Author(s):
|
John Rotondo*+
|
|
Companies:
|
AT&T Labs - Research
|
|
Address:
|
180 Park Ave, Florham Park, NJ, 07932,
|
|
Keywords:
|
2-stage sampling ; optimal sampling ; survey sampling ; satisfaction surveys
|
|
Abstract:
|
The managers responsible for the selection of methodology used in satisfaction surveys were concerned about potential weaknesses in the sampling method used on larger businesses. The traditional procedure was to survey one knowledgeable high-level manager from each sampled firm. However, on an ad hoc basis, multiple raters were drawn from some of the sampled firms, although no statistical framework was available to guide sampling of multiple raters or analysis of multiple rater data. I present an overview of a 2-stage sampling theory which: 1) accommodates multiple raters from each firm; 2) formally incorporates within-firm variation in satisfaction; 3) enables the designer to solve for the optimal number of raters to sample from each sampled firm in accordance with several alternative statistical optimality criteria; 4) provides a foundation for statistical inference.
|
- 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 |
