A Sandwich Standard Error Estimator for Exploratory Factor Analysis With Nonnormal Data and Imperfect Models

Guangjian Zhang; Kristopher J. Preacher; Minami Hattori; Ge Jiang; Lauren A. Trichtinger

doi:10.1177/0146621618798669

A Sandwich Standard Error Estimator for Exploratory Factor Analysis With Nonnormal Data and Imperfect Models

Guangjian Zhang, Kristopher J. Preacher, Minami Hattori, Ge Jiang, Lauren A. Trichtinger

Educational Psychology

Research output: Contribution to journal › Article › peer-review

Abstract

This article is concerned with standard errors (SEs) and confidence intervals (CIs) for exploratory factor analysis (EFA) in different situations. The authors adapt a sandwich SE estimator for EFA parameters to accommodate nonnormal data and imperfect models, factor extraction with maximum likelihood and ordinary least squares, and factor rotation with CF-varimax, CF-quartimax, geomin, or target rotation. They illustrate the sandwich SEs and CIs using nonnormal continuous data and ordinal data. They also compare SE estimates and CIs of the conventional information method, the sandwich method, and the bootstrap method using simulated data. The sandwich method and the bootstrap method are more satisfactory than the information method for EFA with nonnormal data and model approximation error.

Original language	English (US)
Pages (from-to)	360-373
Number of pages	14
Journal	Applied Psychological Measurement
Volume	43
Issue number	5
Early online date	Sep 14 2018
DOIs	https://doi.org/10.1177/0146621618798669
State	Published - Jul 1 2019

Keywords

factor analysis
factor rotation
latent variable models
standard errors

ASJC Scopus subject areas

Social Sciences (miscellaneous)
Psychology (miscellaneous)

Online availability

10.1177/0146621618798669

Library availability

Discover UIUC Full Text

Cite this

@article{bc907746a4754cc98a0b4e3489d1ac3c,

title = "A Sandwich Standard Error Estimator for Exploratory Factor Analysis With Nonnormal Data and Imperfect Models",

abstract = "This article is concerned with standard errors (SEs) and confidence intervals (CIs) for exploratory factor analysis (EFA) in different situations. The authors adapt a sandwich SE estimator for EFA parameters to accommodate nonnormal data and imperfect models, factor extraction with maximum likelihood and ordinary least squares, and factor rotation with CF-varimax, CF-quartimax, geomin, or target rotation. They illustrate the sandwich SEs and CIs using nonnormal continuous data and ordinal data. They also compare SE estimates and CIs of the conventional information method, the sandwich method, and the bootstrap method using simulated data. The sandwich method and the bootstrap method are more satisfactory than the information method for EFA with nonnormal data and model approximation error.",

keywords = "factor analysis, factor rotation, latent variable models, standard errors",

author = "Guangjian Zhang and Preacher, {Kristopher J.} and Minami Hattori and Ge Jiang and Trichtinger, {Lauren A.}",

year = "2019",

month = jul,

day = "1",

doi = "10.1177/0146621618798669",

language = "English (US)",

volume = "43",

pages = "360--373",

journal = "Applied Psychological Measurement",

issn = "0146-6216",

publisher = "SAGE Publications Inc.",

number = "5",

}

TY - JOUR

T1 - A Sandwich Standard Error Estimator for Exploratory Factor Analysis With Nonnormal Data and Imperfect Models

AU - Zhang, Guangjian

AU - Preacher, Kristopher J.

AU - Hattori, Minami

AU - Jiang, Ge

AU - Trichtinger, Lauren A.

PY - 2019/7/1

Y1 - 2019/7/1

N2 - This article is concerned with standard errors (SEs) and confidence intervals (CIs) for exploratory factor analysis (EFA) in different situations. The authors adapt a sandwich SE estimator for EFA parameters to accommodate nonnormal data and imperfect models, factor extraction with maximum likelihood and ordinary least squares, and factor rotation with CF-varimax, CF-quartimax, geomin, or target rotation. They illustrate the sandwich SEs and CIs using nonnormal continuous data and ordinal data. They also compare SE estimates and CIs of the conventional information method, the sandwich method, and the bootstrap method using simulated data. The sandwich method and the bootstrap method are more satisfactory than the information method for EFA with nonnormal data and model approximation error.

AB - This article is concerned with standard errors (SEs) and confidence intervals (CIs) for exploratory factor analysis (EFA) in different situations. The authors adapt a sandwich SE estimator for EFA parameters to accommodate nonnormal data and imperfect models, factor extraction with maximum likelihood and ordinary least squares, and factor rotation with CF-varimax, CF-quartimax, geomin, or target rotation. They illustrate the sandwich SEs and CIs using nonnormal continuous data and ordinal data. They also compare SE estimates and CIs of the conventional information method, the sandwich method, and the bootstrap method using simulated data. The sandwich method and the bootstrap method are more satisfactory than the information method for EFA with nonnormal data and model approximation error.

KW - factor analysis

KW - factor rotation

KW - latent variable models

KW - standard errors

UR - http://www.scopus.com/inward/record.url?scp=85059626619&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059626619&partnerID=8YFLogxK

U2 - 10.1177/0146621618798669

DO - 10.1177/0146621618798669

M3 - Article

SN - 0146-6216

VL - 43

SP - 360

EP - 373

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

IS - 5

ER -

A Sandwich Standard Error Estimator for Exploratory Factor Analysis With Nonnormal Data and Imperfect Models

Abstract

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this