Differential Item Functioning Analysis Without A Priori Information on Anchor Items: QQ Plots and Graphical Test.

摘要: Differential item functioning (DIF) analysis is an important step in establishing the validity of measurements. Most traditional methods for DIF use item-by-item strategy via anchor items that are assumed DIF-free. If flawed, these will yield misleading results due to biased scales. In this article, based on fact item’s relative change difficulty difference (RCD) does not depend mean ability individual groups, a new detection method (RCD-DIF) proposed by comparing observed differences against those with simulated data known The RCD-DIF consists D-QQ (quantile quantile) plot permits identification internal references points (similar items), RCD-QQ facilitates visual examination DIF, and RCD graphical test synchronizes at level confidence intervals items. procedure visually reveals overall pattern size each expected work properly even when majority possess unbalanced. Results two simulation studies indicate has Type I error rate comparable existing but greater power.