A Comparison of Logistic Regression Models for Dif Detection in Polytomous Items: The Effect of Small Sample Sizes and Non-Normality of Ability Distributions

Journal Title: International Journal of Assessment Tools in Education - Year 2015, Vol 2, Issue 1

Abstract

This study investigated the effectiveness of logistic regression models to detect uniform and non-uniform DIF in polytomous items across small sample sizes and non-normality of ability distributions. A simulation study was used to compare three logistic regression models, which were the cumulative logits model, the continuation ratio model, and the adjacent categories model. The results revealed that logistic regression was a powerful method to detect DIF in polytomous items, but not useful to distinguish the type of DIF. Continuation ratio model worked best to detect uniform DIF, but the cumulative logits model gave more acceptable type I error results. As sample size increased, type I errors increased at cumulative logits model results. Skewness of ability distributions reduced power of logistic regression to detect non-uniform DIF. Small sample sizes reduced power of logistic regression.

Authors and Affiliations

Yasemin KAYA, Walter L. LEITE, M. David MILLER

Keywords

Related Articles

Developing The Moral Competencies of Accounting Students: A Case Study of International Islamic University Malaysia (IIUM)

Two decades of financial scandals have seriously damaged the credibility of accountants as guardians of financial information. To repair this credibility, the Malaysian government released a blueprint that mandated Malay...

Perceptions of Organizational Politics Scale (POPS) Questionnaire into Turkish: A Validity and Reliability Study

In this study it was aimed to make the studies of the translation of Perception of Organizational Politics Scale into Turkish and the validity and reliability of the scale. Perceptions of Organizational Politics Scale’s...

The Dif Identification in Constructed Response Items Using Partial Credit Model

The study was to identify the load, the type and the significance of differential item functioning (DIF) in constructed response item using the partial credit model (PCM). The data in the study were the students’ instrum...

The Development of a General Disaster Preparedness Belief Scale Using the Health Belief Model as a Theoretical Framework

The Health Belief Model (HBM) is one of the oldest and most recognized conceptual framework of health behavior and can be applied to disaster preparedness efforts which focus predominantly on human behavior. The study ai...

Parental Perceptions about Children’s Authentic Assessment and the Work Sampling System’s implementation

The authentic assessment process in preschool education gains the confidence of the practices which are used today, as an innovative educational policy in the interest of everyone who’s involved in early childhood educat...

Download PDF file
  • EP ID EP174037
  • DOI -
  • Views 151
  • Downloads 0

How To Cite

Yasemin KAYA, Walter L. LEITE, M. David MILLER (2015). A Comparison of Logistic Regression Models for Dif Detection in Polytomous Items: The Effect of Small Sample Sizes and Non-Normality of Ability Distributions. International Journal of Assessment Tools in Education, 2(1), 22-39. https://europub.co.uk./articles/-A-174037