A processing speed test based on rule-based item generation: An analysis with the Rasch Poisson Counts model

Processing speed capacity refers to the ability to solve easy tasks in a restricted amount of time. The Münster Mental Speed Test (MS2T) employs the technique of rule-based item generation, which allows to easily produce a large amount of individually different items which nevertheless share the same psychometric properties. For a refined measurement of processing speed, the MS2T comprises items covering several content facets (symbolic, numeric, verbal) as well as varying complexity levels. Processing speed test data is often handled in the classical test theory framework, but in this study we fit the Rasch Poisson Counts model (RPCM), an item response theory (IRT) model especially designed for count data. The RPCM shows a good fit to the data and offers further advantages like a refined item analysis, Rasch scalability, and the possibility to employ more elaborate IRT-based techniques like, for example, computerized adaptive testing.