Case based error variance corrected estimation of structural models

TL;DR

This paper introduces a novel data-driven method for estimating structural equation models that can handle non-linear, non-smooth models and various constraints, offering a flexible alternative to traditional covariance-based approaches.

Contribution

It presents a new SEM estimation technique based directly on data, expanding capabilities to non-linear and constrained models, with evaluation through simulations.

Findings

Effective for non-linear models

Handles various constraints

Shows promising simulation results

Abstract

A new method for estimating structural equation models (SEM) is proposed and evaluated. In contrast to most other methods, it is based directly on the data, not on the covariance matrix of the data. The new approach is flexible enough to handle non-linear and non-smooth models and allows to model various constraints. Principle strengths and weaknesses of this approach are discussed and simulation studies are performed to reveal problems and potentials of this approach.