NAEP Assessment IRT Parameters
During scaling, Item Response Theory (IRT) parameters are estimated using data from the current assessment and the most recent past assessment of the same subject if that past assessment was developed according to the same assessment framework. For items fitting the two-parameter IRT model, a and b parameters representing discrimination power and location, respectively, are estimated. For items fitting the three-parameter model, a, b, and c, representing the guessing parameter, are estimated. For the generalized partial-credit model, a, b, and d parameters representing category threshold parameters are estimated. The item parameters reported for NAEP assessments are provided in the metrics used for the original calibration of the scales. Therefore, the parameters are not reported in the metric of the final 0–300 or 0–500 scales, but are reported in the metric of a provisional scale with mean 0 and standard deviation 1.
Last updated 14 July 2008 (DB)
Printer-friendly Version
|