Selection between linear factor models and latent profile models using conditional covariances

Peter F. Halpin, Michael D. Maraun

Research output: Contribution to journalArticle

Abstract

A method for selecting between K-dimensional linear factor models and (K + 1) - class latent profile models is proposed. In particular, it is shown that the conditional covariances of observed variables are constant under factor models but nonlinear functions of the conditioning variable under latent profile models. The performance of a convenient inferential method suggested by the main result is examined via data simulation and is shown to have acceptable error rate control when deciding between the 2 types of models. The proposed test is illustrated using examples from vocational assessment and developmental psychology.

Original languageEnglish (US)
Pages (from-to)910-934
Number of pages25
JournalMultivariate Behavioral Research
Volume45
Issue number6
DOIs
StatePublished - Nov 2010

Fingerprint

Conditional Model
Factor Models
Linear Models
Linear Model
Latent Class
Rate Control
Error Control
Nonlinear Function
Conditioning
Error Rate
Model
Profile
Simulation
Developmental Psychology
Conditioning (Psychology)

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Statistics and Probability

Cite this

Selection between linear factor models and latent profile models using conditional covariances. / Halpin, Peter F.; Maraun, Michael D.

In: Multivariate Behavioral Research, Vol. 45, No. 6, 11.2010, p. 910-934.

Research output: Contribution to journalArticle

@article{dc1972aeec2d4c11bd3385672b2f7c79,
title = "Selection between linear factor models and latent profile models using conditional covariances",
abstract = "A method for selecting between K-dimensional linear factor models and (K + 1) - class latent profile models is proposed. In particular, it is shown that the conditional covariances of observed variables are constant under factor models but nonlinear functions of the conditioning variable under latent profile models. The performance of a convenient inferential method suggested by the main result is examined via data simulation and is shown to have acceptable error rate control when deciding between the 2 types of models. The proposed test is illustrated using examples from vocational assessment and developmental psychology.",
author = "Halpin, {Peter F.} and Maraun, {Michael D.}",
year = "2010",
month = "11",
doi = "10.1080/00273171.2010.532361",
language = "English (US)",
volume = "45",
pages = "910--934",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Psychology Press Ltd",
number = "6",

}

TY - JOUR

T1 - Selection between linear factor models and latent profile models using conditional covariances

AU - Halpin, Peter F.

AU - Maraun, Michael D.

PY - 2010/11

Y1 - 2010/11

N2 - A method for selecting between K-dimensional linear factor models and (K + 1) - class latent profile models is proposed. In particular, it is shown that the conditional covariances of observed variables are constant under factor models but nonlinear functions of the conditioning variable under latent profile models. The performance of a convenient inferential method suggested by the main result is examined via data simulation and is shown to have acceptable error rate control when deciding between the 2 types of models. The proposed test is illustrated using examples from vocational assessment and developmental psychology.

AB - A method for selecting between K-dimensional linear factor models and (K + 1) - class latent profile models is proposed. In particular, it is shown that the conditional covariances of observed variables are constant under factor models but nonlinear functions of the conditioning variable under latent profile models. The performance of a convenient inferential method suggested by the main result is examined via data simulation and is shown to have acceptable error rate control when deciding between the 2 types of models. The proposed test is illustrated using examples from vocational assessment and developmental psychology.

UR - http://www.scopus.com/inward/record.url?scp=78650485726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650485726&partnerID=8YFLogxK

U2 - 10.1080/00273171.2010.532361

DO - 10.1080/00273171.2010.532361

M3 - Article

VL - 45

SP - 910

EP - 934

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

IS - 6

ER -