Back

ABSTRACT

Detecting Measurement Distrubance Effects: The Graphical Display of Item Characteristics

Traditional identification of misfitting items in Rasch measurement models has interpreted the Infit and Outfit z standardized statistic. A more recent approach made possible by Winsteps is to specify “group = 0” in the control file and subsequently view the item characteristic curve for each item against the true probability curve. The graphical display reveals whether an item follows the true probability curve or deviates substantially, thus indicating measurement disturbance. Probability of item response and logit ability are easily copied to the clipboard and pasted into Microsoft Excel. An example control file, output item data, and subsequent preparation of an overlay graph for acceptable items and misfit items are presented using Winsteps and Microsoft Excel. For comparison purposes the data are also subjected to an analysis using the MD mapping procedure.

Download Full Article