|
Activity Number:
|
343
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #309607 |
|
Title:
|
Statistical Inference in the Presence of Panel Segmentation in Ranking Data
|
|
Author(s):
|
Lin Xie*+ and Paul I. Nelson
|
|
Companies:
|
Kansas State University and Kansas State University
|
|
Address:
|
101 Dickens Hall, Manhattan, KS, 66506,
|
|
Keywords:
|
Panel segmentation ; Probability distance model ; Ranking data ; Parameter estimation ; Simulation study
|
|
Abstract:
|
Ranking scales are common in sensory evaluations carried out by a panel of judges. Mallows (1957) developed a two parameter distance probability model for analyzing these data. Segmentation refers to situations where the panel consists of sub-groups of judges whose rankings tend to agree. We use mixtures of Mallows distance distributions to model segmentation. This report develops and explores parameter estimation for these models.
|
