Creating performance categories from continuous motor skill data using a Rasch measurement model

This paper reports the use of the Extended Logistic Model (ELM) of Rasch (Andrich, 1988), based on Item Response Theory, to validate the reduction of continuous motor skill data to categories of performance. The data were gathered from the performances of 5 and 6 year old children on 24 fundamental movement skills and involved different measurement units such as seconds, centimetres, scores and counts. In order to compare results across all skills the data were collapsed into discrete sets of categories. Several alternative cut-off locations based on normative data were considered. A feature of the ELM is that it can account for correct scoring of the response categories, but only if the threshold estimates derived from the data by the measurement model are correctly ordered in a hierarchical fashion, from lowest to highest. Should this be the case, a valid scoring function has been established. In this study, the data were successfully reduced to three categories based on the 15th and 85th percentile allowing further analysis to proceed.