Scoring Methods and Measurement Properties of Health Status Measures: AnEmpirical Comparison of Summative and Item Response Theory Scoring for the SF-36 Physical Functioning Scale. Abstract and Executive Summary of Dissertation

摘要

Summative scoring has been a popular method of scoring multi-item scales.However, this approach has been criticized for producing scores with only ordinal properties and some researchers have suggested that item response theory (IRT) may be a more attractive scoring alternative. However, empirical evidence of its usefulness for scoring health status instruments has been limited. Using data from studies of asthma, end-stage renal disease, and previously injured subjects, as well as a random sample of the general U.S. population, the effect of IRT and summative scoring on the measurement precision and responsiveness of the 10-item SF-36 physical functioning scale was compared. The nature of score assignment under the two methods was described and their consequent effects on the standard error of measurement, score distribution, score variance, and instrument responsiveness was examined. Results suggest that item response theory can provide improvements in score precision and instrument responsiveness. However, these benefits may not be generalizable to other health status instruments and experimental conditions. A priority for future research would be to determine the conditions under which the measurement framework offered by item response theory would prove most beneficial.