|
Activity Number:
|
228
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Defense and National Security
|
| Abstract - #303911 |
|
Title:
|
Opinion Pooling on Maps
|
|
Author(s):
|
Jonathan Wilson*+ and Kristin Duncan
|
|
Companies:
|
San Diego State University and San Diego State University
|
|
Address:
|
, , ,
|
|
Keywords:
|
Opinion Pooling ; Geometric Mean
|
|
Abstract:
|
Analysts are often tasked with pooling the opinions of experts. We consider the case where experts' opinions are probability distributions over a discrete sample space, such as grid points of a map. We illustrate the advantageous and problematic features of the commonly used arithmetic and logarithmic aggregation techniques in this situation. A hybrid pooling operator that adds a constant to the computation of the geometric mean and subtracts out this constant at the end is examined and shown to be preferable to arithmetic and logarithmic pooling in some instances. The asymptotic properties of the hybrid operator are derived and recommendations are made for the choice of the constant.
|
- 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 2009 program |
