Latent Variable Models Under Misspecification: Two-Stage Least Squares (2SLS) and Maximum Likelihood (ML) Estimators
- 1 August 2007
- journal article
- research article
- Published by SAGE Publications in Sociological Methods & Research
- Vol. 36 (1), 48-86
- https://doi.org/10.1177/0049124107301947
Abstract
This article compares maximum likelihood (ML) estimation to three variants of two-stage least squares (2SLS) estimation in structural equation models. The authors use models that are both correctly and incorrectly specified. Simulated data are used to assess bias, efficiency, and accuracy of hypothesis tests. Generally, 2SLS with reduced sets of instrumental variables performs similarly to ML when models are correctly specified. Under correct specification, both estimators have little bias except at the smallest sample sizes and are approximately equally efficient. As predicted, when models are incorrectly specified, 2SLS generally performs better, with less bias and more accurate hypothesis tests. Unless a researcher has tremendous confidence in the correctness of his or her model, these results suggest that a 2SLS estimator should be considered.Keywords
This publication has 35 references indexed in Scilit:
- Automating the Selection of Model-Implied Instrumental VariablesSociological Methods & Research, 2004
- A Note on a Two-stage Least Squares Estimator for Higher-order Factor AnalysesSociological Methods & Research, 2002
- Interactions of latent variables in structural equation modelsStructural Equation Modeling: A Multidisciplinary Journal, 1998
- Analytical Small-Sample Distribution Theory in Econometrics: The Simultaneous-Equations CaseInternational Economic Review, 1982
- A Comparative Monte Carlo Study of the Properties of Econometric EstimatorsJournal of the American Statistical Association, 1975
- The Exact Sampling Distribution of Ordinary Least Squares and Two-Stage Least Squares EstimatorsJournal of the American Statistical Association, 1969
- On the Relative Small-Sample Properties of Several Structural-Equation EstimatorsEconometrica, 1967
- On Finite Sample Distributions of Generalized Classical Linear Identifiability Test StatisticsJournal of the American Statistical Association, 1960
- A Generalized Classical Method of Linear Estimation of Coefficients in a Structural EquationEconometrica, 1957
- Estimation of the Parameters of a Single Equation in a Complete System of Stochastic EquationsThe Annals of Mathematical Statistics, 1949