Abstract
The purpose of this study was to apply the bootstrap procedure to evaluate how the bootstrapped confidence intervals (CIs) for polytomous Rasch fit statistics might differ according to sample sizes and test lengths in comparison with the rule-of-thumb critical value of misfit. A total of 25 simulated data sets were generated to fit the Rasch measurement and then a total of 1,000 replications were conducted to compute the bootstrapped CIs under each of 25 testing conditions. The results showed that rule-of-thumb critical values for assessing the magnitude of misfit were not applicable because the infit and outfit mean square error statistics showed different magnitudes of variability over testing conditions and the standardized fit statistics did not exactly follow the standard normal distribution. Further, they also do not share the same critical range for the item and person misfit. Based on the results of the study, the bootstrapped CIs can be used to identify misfitting items or persons as they offer a reasonable alternative solution, especially when the distributions of the infit and outfit statistics are not well known and depend on sample size.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call