uu.seUppsala University Publications
Change search
ReferencesLink to record
Permanent link

Direct link
A Simulation Study of Polychoric Instrumental Variable Estimation in Structural Equation Models
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Statistics.
Department of Sociology, Tsinghua University.
Uppsala University, Disciplinary Domain of Humanities and Social Sciences, Faculty of Social Sciences, Department of Statistics.
2016 (English)In: Structural Equation Modeling, ISSN 1070-5511, E-ISSN 1532-8007, Vol. 23, no 5, 680-694 p.Article in journal (Refereed) Published
Abstract [en]

Data collected from questionnaires are often in ordinal scale. Unweighted least squares

(ULS), diagonally weighted least squares (DWLS) and normal-theory maximum likelihood

(ML) are commonly used methods to fit structural equation models (SEMs). Consistency

of these estimators demands no structural misspecification. In this paper, we conduct a

simulation study to compare the equation-by-equation polychoric instrumental variable

(PIV) estimation with ULS, DWLS, and ML. Accuracy of PIV for the correctly specified

model and robustness of PIV for misspecified models are investigated through a

confirmatory factor analysis (CFA) model and a SEM with ordinal indicators. The effects

of sample size and non-normality of the underlying continuous variables are also examined.

The simulation results show that PIV produces robust factor loading estimates in the CFA

model and in SEM. PIV also produces robust path coefficient estimates in the model where

valid instruments are used. However, robustness highly depends on the validity of

instruments.

Place, publisher, year, edition, pages
Routledge, 2016. Vol. 23, no 5, 680-694 p.
Keyword [en]
ordinal data, factor analysis, robustness, model misspecification
National Category
Social Sciences
Research subject
Statistics
Identifiers
URN: urn:nbn:se:uu:diva-293591DOI: 10.1080/10705511.2016.1189334OAI: oai:DiVA.org:uu-293591DiVA: diva2:928017
Available from: 2016-05-13 Created: 2016-05-13 Last updated: 2016-09-08

Open Access in DiVA

No full text

Other links

Publisher's full texthttp://www.tandfonline.com.ezproxy.its.uu.se/doi/pdf/10.1080/10705511.2016.1189334?needAccess=true
By organisation
Department of Statistics
In the same journal
Structural Equation Modeling
Social Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 153 hits
ReferencesLink to record
Permanent link

Direct link