Activity Number:
|
41
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 11, 2002 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Section on Survey Research Methods*
|
Abstract - #301145 |
Title:
|
An Evaluation of Estimation Strategies for the Intra-clustering Correlation Coefficient
|
Author(s):
|
Ruby Johnson*+ and Jun Liu+
|
Affiliation(s):
|
RTI International and RTI International
|
Address:
|
1606 Cheshire Bridge Road, Durham, North Carolina, 27712, USA 3040 Cornwallis Road, RTP, North Carolina, 27709, USA
|
Keywords:
|
Multi-stage Design ; Intra-cluster Correlation Coefficient ; Design Consistent Variance Components Estimation
|
Abstract:
|
The intra-cluster correlation coefficient rho is a critical parameter from study design to study evaluation. A good strategy for estimating the intra-cluster correlation coefficient is very important. The most popular method of estimating the parameter is through formulas suggested in Kish (1965), where simple random sampling is assumed for both stages of selection. A design-consistent variance component formula given by Liu, et al. (1998) provides an alternative method. In this paper, we evaluate different methods for estimating the parameter through simulations.
|