Miivfind: A Command for Identifying Model-Implied Instrumental Variables for Structural Equation Models in Stata

Abstract

This article presents a new Stata command, miivfind, that implements an algorithm developed by Bollen and Bauer (2004, Sociological Methods and Research 32: 425–452) to find the model-implied instrumental variables (MIIVs) from an identified structural equation model. MIIVs allow researchers to draw on instrumental-variable estimators, such as two-stage least-squares estimators, to obtain estimates for the parameters of a hypothesized structural equation model. It can be difficult to identify MIIVs by inspection of either a diagram of the model or the model equations. Two examples are provided that illustrate the use of miivfind to identify MIIVs and some of the advantages of a MIIV estimator as compared with a maximum likelihood estimator. By assisting in the process of finding MIIVs, miivfind facilitates the use of an alternative class of estimators, instrumental-variable estimators, to the standard maximum-likelihood and asymptotic-distribution free estimators available for structural equation models.