|
Activity Number:
|
210
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 7, 2006 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Consulting
|
| Abstract - #307464 |
|
Title:
|
Characterizations of Factor Analytic Covariance Structure
|
|
Author(s):
|
Timothy Costigan*+
|
|
Companies:
|
Eli Lilly and Company
|
|
Address:
|
Lilly Corporate Center, Indianapolis, IN, 46285,
|
|
Keywords:
|
probability inequalities ; multiple testing ; multivariate normal
|
|
Abstract:
|
We show that trivariate normal distributions exhibit the factor analytic covariance structure if and only if all correlations are non-negative and all partial correlations are positive. These conditions, which are also necessary and sufficient for MTP2,are used to obtain factor analytic upper and lower bounds to higher order orthant and rectangular probabilities. A simple expression is also presented for trivariate normal distributions to be MTP2 in absolute value. These characterizations are used to derive second/third order hybrid probability inequalities that can be evaluated in SAS. Examples are presented to illustrate the accuracy of the new bounds.
|
- 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 2006 program |
