DIF statistical inference without knowing anchoring items
From MaRDI portal
Abstract: Establishing the invariance property of an instrument is a key step for establishing its measurement validity. Measurement invariance is typically assessed by differential item functioning (DIF) analysis, i.e., detecting DIF items whose response distribution depends on not only the latent trait measured by the instrument but also the group membership. DIF analysis is confounded by the group difference in the latent trait distributions. Many DIF analyses require knowing several anchor items that are DIF-free to draw inferences on whether each of the rest is a DIF item, where the anchor items are used to identify the latent trait distributions. When no prior information on anchor items is available, item purification methods and regularized estimation methods can be used. The former iteratively purifies the anchor set by a stepwise model selection procedure, and the latter selects the DIF-free items by a LASSO-type regularization approach. Unfortunately, unlike the methods based on a correctly specified anchor set, these methods are not guaranteed to provide valid statistical inference (e.g., confidence intervals and -values). In this paper, we propose a new method for DIF analysis under a multiple indicators and multiple causes (MIMIC) model for DIF. This method adopts a minimal norm condition for identifying the latent trait distributions. Without requiring prior knowledge about an anchor set, it can accurately estimate the DIF effects of individual items and further draw valid statistical inferences for quantifying the uncertainty. Specifically, the inference results allow us to control the type-I error for DIF detection, which may not be possible with item purification and regularized estimation methods. The proposed method is applied to analyzing the three personality scales of the Eysenck personality questionnaire - revised (EPQ-R).
Recommendations
- Differential item functioning analysis without a priori information on anchor items: QQ plots and graphical test
- DIF analysis with unknown groups and anchor items
- Differential item functioning via robust scaling
- Modeling and testing differential item functioning in unidimensional binary item response models with a single continuous covariate: a functional data analysis approach
- A penalty approach to differential item functioning in Rasch models
Cites work
- A model-based standardization approach that separates true bias/DIF from group ability differences and detects test bias/DTF as well as item bias/DIF
- A penalized likelihood method for multi‐group structural equation modelling
- A penalty approach to differential item functioning in Rasch models
- A statistical test for differential item pair functioning
- Asymptotic Statistics
- Differential item functioning analysis without a priori information on anchor items: QQ plots and graphical test
- Estimating the dimension of a model
- Estimation of Regression Relationships Containing Unobservable Independent Variables
- scientific article; zbMATH DE number 5957408 (Why is no real title available?)
- scientific article; zbMATH DE number 621792 (Why is no real title available?)
- scientific article; zbMATH DE number 720689 (Why is no real title available?)
- scientific article; zbMATH DE number 1104922 (Why is no real title available?)
- scientific article; zbMATH DE number 845714 (Why is no real title available?)
- scientific article; zbMATH DE number 3297790 (Why is no real title available?)
- Item-focussed trees for the identification of items in differential item functioning
- Lasso-type recovery of sparse representations for high-dimensional data
- On the conditions used to prove oracle results for the Lasso
- Quantile regression.
- Rasch trees: a new method for detecting differential item functioning in the Rasch model
- The area between two item characteristic curves
Cited in
(7)- DIF analysis with unknown groups and anchor items
- Statistical inference for covariate-adjusted and interpretable generalized latent factor model with application to testing fairness
- Reducing differential item functioning via process data
- Detecting differential item functioning across multiple groups using group pairwise penalty
- Multi-group regularized Gaussian variational estimation: fast detection of DIF
- Rejoinder: item response theory -- a statistical framework for educational and psychological measurement
- Comment: wondering and mind-wandering thoughts on IRT
This page was built for publication: DIF statistical inference without knowing anchoring items
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6198856)
