Open AccessBlock-Wise Model Fit for Structural Equation Models With Experience Sampling Data
Author(s) -
Julia Norget,
Axel Mayer
Publication year - 2022
Publication title -
zeitschrift für psychologie
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.037
H-Index - 24
eISSN - 2190-8370
pISSN - 2151-2604
DOI - 10.1027/2151-2604/a000482
Subject(s) - block (permutation group theory) , covariance , variance (accounting) , structural equation modeling , statistics , sampling (signal processing) , mathematics , covariance matrix , econometrics , computer science , geometry , accounting , filter (signal processing) , business , computer vision
. Common model fit indices behave poorly in structural equation models for experience sampling data which typically contain many manifest variables. In this article, we propose a block-wise fit assessment for large models as an alternative. The entire model is estimated jointly, and block-wise versions of common fit indices are then determined from smaller blocks of the variance-covariance matrix using simulated degrees of freedom. In a first simulation study, we show that block-wise fit indices, contrary to global fit indices, correctly identify correctly specified latent state-trait models with 49 occasions and N = 200. In a second simulation, we find that block-wise fit indices cannot identify misspecification purely between days but correctly rejects other misspecified models. In some cases, the block-wise fit is superior in judging the strength of the misspecification. Lastly, we discuss the practical use of block-wise fit evaluation and its limitations.