|
Activity Number:
|
405
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #302262 |
|
Title:
|
Exact and REML-Based Confidence Intervals for Variance Components Using Non-Normal Distributions
|
|
Author(s):
|
Brent Burch*+
|
|
Companies:
|
Northern Arizona University
|
|
Address:
|
Department of Mathematics & Statisitics, Flagstaff, AZ, 86011-5717,
|
|
Keywords:
|
linear mixed models ; heritability ; variance components ; REML ; confidence intervals
|
|
Abstract:
|
Using normality assumptions, one can compute exact confidence intervals for variance components. Exact intervals differ from intervals that are based on the asymptotic distribution of restricted maximum likelihood (REML) estimators. Simulation studies are conducted to evaluate the performance of the exact and the REML-based intervals when the observations are not normally distributed. Simulated coverage probabilities and expected lengths provide guidance as to which interval procedure is favored for a particular scenario. Confidence intervals for heritability, a particular function of variance components, are also considered.
|
- 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 2008 program |
