Latent variable forests for latent variable score estimation

PDF
classe-kern-2024-detecting-differential-item-functioning-in-multidimensional-graded-response-models-with-recursive.pdf - Veröffentlichte Version
Download (766kB)

DOI:	https://doi.org/10.1177/00131644241237502
URL:	https://journals.sagepub.com/doi/full/10.1177/0013...
URN:	urn:nbn:de:bsz:180-madoc-669886
Dokumenttyp:	Zeitschriftenartikel
Erscheinungsjahr:	2024
Titel einer Zeitschrift oder einer Reihe:	Educational and Psychological Measurement : EPM
Band/Volume:	84
Heft/Issue:	6
Seitenbereich:	1138-1172
Ort der Veröffentlichung:	Thousand Oaks, Calif. [u.a.]
Verlag:	Sage Periodicals Press
ISSN:	0013-1644
Sprache der Veröffentlichung:	Englisch
Einrichtung:	Außerfakultäre Einrichtungen > MZES - Arbeitsbereich A
Bereits vorhandene Lizenz:	Creative Commons Namensnennung 4.0 International (CC BY 4.0)
Fachgebiet:	310 Statistik
Abstract:	We develop a latent variable forest (LV Forest) algorithm for the estimation of latent variable scores with one or more latent variables. LV Forest estimates unbiased latent variable scores based on confirmatory factor analysis (CFA) models with ordinal and/or numerical response variables. Through parametric model restrictions paired with a nonparametric tree-based machine learning approach, LV Forest estimates latent variable scores using models that are unbiased with respect to relevant subgroups in the population. This way, estimated latent variable scores are interpretable with respect to systematic influences of covariates without being biased by these variables. By building a tree ensemble, LV Forest takes parameter heterogeneity in latent variable modeling into account to capture subgroups with both good model fit and stable parameter estimates. We apply LV Forest to simulated data with heterogeneous model parameters as well as to real large-scale survey data. We show that LV Forest improves the accuracy of score estimation if parameter heterogeneity is present.