Test Purification and the Evaluation of Differential Item Functioning with Multinomial Logistic Regression

Summary We conducted a computer simulation study to determine the effect of using an iterative or noniterative multinomial logistic regression analysis (MLR) to detect differential item functioning (DIF) in polytomous items. A simple iteration in which ability is defined as total observed score in the test is compared with a two-step MLR in which the ability was purified by eliminating the DIF items. Data were generated to simulate several biased tests. The factors manipulated were: DIF effect size (0.5, 1.0, and 1.5), percentage of DIF items in the test (0%, 10%, 20% and 30%), DIF type (uniform and nonuniform) and sample size (500, 1000 and 2000). Item scores were generated using the graded response model. The MLR procedures were consistently able to detect both uniform and nonuniform DIF. When the two-step MLR procedure was used, the false-positive rate (the proportion of non-DIF items that were detected as DIF) decreased and the correct identification rate increased slightly. The purification process results in an improvement in the correct detection rate only in uniform DIF, large sample size, and large amount of DIF conditions. For nonuniform DIF there is no difference between the MLR-WP and MLR-TP procedures.

Download Full-text

A Simulation Study to Assess the Effect of the Number of Response Categories on the Power of Ordinal Logistic Regression for Differential Item Functioning Analysis in Rating Scales

Computational and Mathematical Methods in Medicine ◽

10.1155/2016/5080826 ◽

2016 ◽

Vol 2016 ◽

pp. 1-8 ◽

Cited By ~ 3

Author(s):

Elahe Allahyari ◽

Peyman Jafari ◽

Zahra Bagheri

Keyword(s):

Logistic Regression ◽

Sample Size ◽

Differential Item Functioning ◽

Rating Scales ◽

Error Rates ◽

Ordinal Logistic Regression ◽

Type I ◽

Item Functioning ◽

Quality Of Life Scale ◽

The Impact

Objective.The present study uses simulated data to find what the optimal number of response categories is to achieve adequate power in ordinal logistic regression (OLR) model for differential item functioning (DIF) analysis in psychometric research.Methods.A hypothetical ten-item quality of life scale with three, four, and five response categories was simulated. The power and type I error rates of OLR model for detecting uniform DIF were investigated under different combinations of ability distribution (θ), sample size, sample size ratio, and the magnitude of uniform DIF across reference and focal groups.Results.Whenθwas distributed identically in the reference and focal groups, increasing the number of response categories from 3 to 5 resulted in an increase of approximately 8% in power of OLR model for detecting uniform DIF. The power of OLR was less than 0.36 when ability distribution in the reference and focal groups was highly skewed to the left and right, respectively.Conclusions.The clearest conclusion from this research is that the minimum number of response categories for DIF analysis using OLR is five. However, the impact of the number of response categories in detecting DIF was lower than might be expected.

Download Full-text

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

BioMed Research International ◽

10.1155/2020/1632350 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Marjan Faghih ◽

Zahra Bagheri ◽

Dejan Stevanovic ◽

Seyyed Mohhamad Taghi Ayatollahi ◽

Peyman Jafari

Keyword(s):

Logistic Regression ◽

Maximum Likelihood ◽

Sample Size ◽

Differential Item Functioning ◽

Bias Correction ◽

Rare Events ◽

Estimation Methods ◽

Type I ◽

Item Functioning ◽

Events Data

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 (τ). Indeed, as compared with WLR and for severe imbalanced degree (τ = 0.069), there were reductions of approximately 30% and 24% under DIF = 0.4 and 27% and 23% under DIF = 0.8 in the power of the PML and ML, respectively. The present study revealed that the WLR outperforms both the ML and PML estimation methods when logistic regression is used to evaluate DIF for imbalanced or rare events data.

Download Full-text

Power and Sample Size Calculations for Logistic Regression Tests for Differential Item Functioning

Journal of Educational Measurement ◽

10.1111/jedm.12058 ◽

2014 ◽

Vol 51 (4) ◽

pp. 441-462 ◽

Cited By ~ 3

Author(s):

Zhushan Li

Keyword(s):

Logistic Regression ◽

Sample Size ◽

Differential Item Functioning ◽

Item Functioning ◽

Sample Size Calculations ◽

Regression Tests

Download Full-text

Evolving High-Tech Collaborations: A Multinomial Logistic Regression Analysis of Innovator Group Size Changes in the Production of Patented Inventions

SSRN Electronic Journal ◽

10.2139/ssrn.2102072 ◽

2012 ◽

Author(s):

Richard Gruner

Keyword(s):

Logistic Regression ◽

Regression Analysis ◽

Group Size ◽

Logistic Regression Analysis ◽

Multinomial Logistic Regression ◽

High Tech ◽

Multinomial Logistic Regression Analysis ◽

Patented Inventions

Download Full-text

Association between Social Integration and Face Mask Use Behavior during the SARS-CoV-2 Pandemic in Japan: Results from U-CORONA Study

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18094717 ◽

2021 ◽

Vol 18 (9) ◽

pp. 4717

Author(s):

Nobutoshi Nawa ◽

Yui Yamaoka ◽

Yuna Koyama ◽

Hisaaki Nishimura ◽

Shiro Sonoda ◽

...

Keyword(s):

Logistic Regression ◽

Regression Analysis ◽

Social Network ◽

Social Integration ◽

Response Bias ◽

Multinomial Logistic Regression ◽

Face Mask ◽

Neighborhood Association ◽

Multinomial Logistic Regression Analysis ◽

Use Behavior

Face mask use is a critical behavior to prevent the spread of SARS-CoV-2. We aimed to evaluate the association between social integration and face mask use during the COVID-19 pandemic in a random sample of households in Utsunomiya City, Greater Tokyo, Japan. Data included 645 adults in the Utsunomiya COVID-19 seROprevalence Neighborhood Association (U-CORONA) study, which was conducted after the first wave of the pandemic, between 14 June 2020 and 5 July 2020, in Utsunomiya City. Social integration before the pandemic was assessed by counting the number of social roles, based on the Cohen’s social network index. Face mask use before and during the pandemic was assessed by questionnaire, and participants were categorized into consistent mask users, new users, and current non-users. Multinomial logistic regression analysis was used to examine the association between lower social integration score and face mask use. To account for possible differential non-response bias, non-response weights were used. Of the 645 participants, 172 (26.7%) were consistent mask users and 460 (71.3%) were new users, while 13 (2.0%) were current non-users. Lower social integration level was positively associated with non-users (RRR: 1.76, 95% CI: 1.10, 2.82). Social integration may be important to promote face mask use.

Download Full-text