Shopping for Efficient Confidence Intervals in Structural Equation Models

by Donna L. Mohr and Yong Xu.

Abstract: Most users of Structural Equation Models are aware that Wald-type standard errors for parameter estimates can vary remarkably depending on the arbitrary choice of how the scale is identified. A simple example shows that confidence intervals based on the likelihood ratio exhibit the same problem. A series of examples suggests that shopping for the scale identification that gives the best relative precision for a certain parameter has very little negative impact on coverage probabilities, and can yield substantially tighter confidence intervals.

Key Words: structural equation models, SEM, likelihood ratio, scale identification, confidence intervals

Authors:
Donna L. Mohr, dmohr@unf.edu
Yong Xu, xuyong007@hotmail.com

Editor: Dayanand Naik, dnaik@odu.edu

READING THE ARTICLE: You can read the article in portable document (.pdf) format (162317 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2333 times since July 24, 2006.


Return to the InterStat Home Page.