The purpose of this study was to compare Type I error rates and power for Mantel-Haenszel (MH) and logistic regression (LR) tests for reference and focal groups with varying ability distributions, sample size and sample size ratios. In this study WinGen3 was used to simulate ability estimates and to generate response data. The two-parameter logistic item response model was used to generate the item parameters for both non-DIF and DIF items. The results showed that with equal group distribution, Type I error rates of MH and LR techniques had similar and near the nominal α level. On the other hand, with unequal group distribution, inflated Type I error rates were observed in MH and LR procedures. Furthermore, the highest type I error rates were observed when difference between ability distributions was high and sample size was large. Results also showed that conditions leading to type I error rate inflation also result in artificially enhanced power rates.

Detecting DIF in polytomous items: An empirical comparison of the ordinal logistic regression, logistic discriminant function analysis, Mantel, and Generalized Mantel-Haenszel procedures.

Değişen Madde Fonksiyonunu Belirlemede Mantel-Haenszel ve Lojistik Regresyon Tekniklerinin Karşilaştirilmasi * Comparison of Mantel-Haenszel and Logistic Regression Techniques in Detecting Differential Item Functioning

A log-linear model (LLM) is a well-known statistical method to examine the relationship among categorical variables. This study investigated the performance of LLM in detecting differential item functioning (DIF) for polytomously scored items via simulations where various sample sizes, ability mean differences (impact), and DIF types were manipulated. Also, the performance of LLM was compared with that of other observed score-based DIF methods, namely ordinal logistic regression, logistic discriminant function analysis, Mantel, and generalized Mantel-Haenszel, regarding their Type I error (rejection rates) and power (DIF detection rates). For the observed score matching stratification in LLM, 5 and 10 strata were used. Overall, generalized Mantel-Haenszel and LLM with 10 strata showed better performance than other methods, whereas ordinal logistic regression and Mantel showed poor performance in detecting balanced DIF where the DIF direction is opposite in the two pairs of categories and partial DIF where DIF exists only in some of the categories.

background or methods or result

https://journals.sagepub.com/doi/pdf/10.1177/0013164419853000

A Log-Linear Modeling Approach for Differential Item Functioning Detection in Polytomously Scored Items.

https://www.ruor.uottawa.ca/bitstream/10393/9373/1/NQ66160.PDF

Detecting DIF in polytomous items: An empirical comparison of the ordinal logistic regression, logistic discriminant function analysis, Mantel, and Generalized Mantel-Haenszel procedures.

Citations

Değişen Madde Fonksiyonunu Belirlemede Mantel-Haenszel ve Lojistik Regresyon Tekniklerinin Karşilaştirilmasi * Comparison of Mantel-Haenszel and Logistic Regression Techniques in Detecting Differential Item Functioning

A Log-Linear Modeling Approach for Differential Item Functioning Detection in Polytomously Scored Items.

Related Papers (5)

The performance of the Mantel-Haenszel and logistic regression DIF identification procedures with real data.

Item Discrimination and Type I Error Rates in DIF Detection Using the Mantel-Haenszel and Logistic Regression Procedures

Overview of logistic regression model analysis and application

Logistic Regression. A Self- Learning Text

Discriminant analysis and logistic regression