EM estimation of a Structural Equation Model

TL;DR

This paper introduces an EM-based estimation method for Structural Equation Models that estimates both model coefficients and latent factors, demonstrating its effectiveness through simulations and real data application.

Contribution

The paper presents a novel EM algorithm for SEM estimation that jointly estimates coefficients and latent factors, improving accuracy and efficiency.

Findings

The method accurately estimates model parameters in simulations.

It effectively recovers latent factors from data.

Application to environmental data demonstrates practical utility.

Abstract

In this work, we propose a new estimation method of a Structural Equation Model. Our method is based on the EM likelihood-maximization algorithm. We show that this method provides estimators, not only of the coefficients of the model, but also of its latent factors. Through a simulation study, we investigate how fast and accurate the method is, and then apply it to real environmental data.