A Comparative Study of the Bias Correction Methods for Differential Item Functioning Analysis in Logistic Regression with Rare Events Data.


Journal

BioMed research international
ISSN: 2314-6141
Titre abrégé: Biomed Res Int
Pays: United States
ID NLM: 101600173

Informations de publication

Date de publication:
2020
Historique:
received: 25 09 2019
revised: 19 12 2019
accepted: 20 01 2020
entrez: 19 3 2020
pubmed: 19 3 2020
medline: 5 1 2021
Statut: epublish

Résumé

The logistic regression (LR) model for assessing differential item functioning (DIF) is highly dependent on the asymptotic sampling distributions. However, for rare events data, the maximum likelihood estimation method may be biased and the asymptotic distributions may not be reliable. In this study, the performance of the regular maximum likelihood (ML) estimation is compared with two bias correction methods including weighted logistic regression (WLR) and Firth's penalized maximum likelihood (PML) to assess DIF for imbalanced or rare events data. The power and type I error rate of the LR model for detecting DIF were investigated under different combinations of sample size, moderate and severe magnitudes of uniform DIF (DIF = 0.4 and 0.8), sample size ratio, number of items, and the imbalanced degree (

Identifiants

pubmed: 32185193
doi: 10.1155/2020/1632350
pmc: PMC7060847
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

1632350

Informations de copyright

Copyright © 2020 Marjan Faghih et al.

Déclaration de conflit d'intérêts

The authors declare no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.

Références

Value Health. 2011 Sep-Oct;14(6):872-83
pubmed: 21914509
Eval Health Prof. 2005 Sep;28(3):283-94
pubmed: 16123258
Stat Med. 2016 Mar 30;35(7):1159-77
pubmed: 26514699
Stat Med. 2002 Aug 30;21(16):2409-19
pubmed: 12210625
Qual Life Res. 2007;16 Suppl 1:69-84
pubmed: 17554640
Epidemiol Psychiatr Sci. 2017 Aug;26(4):430-440
pubmed: 27353487
Comput Methods Programs Biomed. 2003 Jun;71(2):181-7
pubmed: 12758140
Comput Math Methods Med. 2016;2016:5080826
pubmed: 27403207
Child Psychiatry Hum Dev. 2016 Apr;47(2):291-304
pubmed: 26184967
Psychometrika. 2015 Mar;80(1):21-43
pubmed: 24297435
Biometrics. 2009 Dec;65(4):1262-9
pubmed: 19432786
Stat Med. 2017 Jun 30;36(14):2302-2317
pubmed: 28295456
Appl Psychol Meas. 2017 Jan;41(1):30-43
pubmed: 29881077
Proc R Soc Lond A Math Phys Sci. 1946;186(1007):453-61
pubmed: 20998741
Front Psychol. 2018 Jul 27;9:1302
pubmed: 30100891

Auteurs

Marjan Faghih (M)

Department of Biostatistics, Faculty of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.

Zahra Bagheri (Z)

Department of Biostatistics, Faculty of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.

Dejan Stevanovic (D)

Clinic for Neurology and Psychiatry for Children and Youth, Belgrade, Serbia.

Seyyed Mohhamad Taghi Ayatollahi (SMT)

Department of Biostatistics, Faculty of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.

Peyman Jafari (P)

Department of Biostatistics, Faculty of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.

Articles similaires

Vancomycin Polyesters Anti-Bacterial Agents Models, Theoretical Drug Liberation
Humans Meta-Analysis as Topic Sample Size Models, Statistical Computer Simulation
1.00
Iran Environmental Monitoring Seasons Ecosystem Forests
1.00
Humans Machine Learning Thyroid Diseases Logistic Models Male

Classifications MeSH