|
Activity Number:
|
560
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Social Statistics Section
|
| Abstract - #304985 |
|
Title:
|
Identification of Latent Structure: Inside or Outside Structural Equation Model?
|
|
Author(s):
|
Hee-Choon Shin*+
|
|
Companies:
|
NORC at the University of Chicago
|
|
Address:
|
1155 E. 60th St., Rm. 376A, Chicago, IL, 60637,
|
|
Keywords:
|
Structural Equation Modeling ; Measurement Model ; Latent Structure ; Chi-Square
|
|
Abstract:
|
For the last several decades, structural equation models (SEMs) have been utilized to model complex relationships in social and behavioral sciences. SEMs are characterized by two components, namely the structural model and the measurement model(s). The research question of this paper is related to the specification of the measurement model(s). There can be two ways to specify unmeasured latent variable(s) in the structural equation modeling. First, we could measure the unmeasured latent variable(s) using manifest variables before specifying structural model. Then we could specify a structural model with the identified latent variable(s). Secondly, we could specify both of the measurement and structural models at the same time. Our research is to show the advantages and disadvantages of the two approaches.
|
- 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 |
