ERIC Number: ED368788
Record Type: RIE
Publication Date: 1994-Apr
Reference Count: N/A
Examining Replication Effects in Rasch Fit Statistics.
Schumacker, Randall E.; And Others
Rasch between and total weighted and unweighted fit statistics were compared using varying test lengths and sample sizes. Two test lengths (20 and 50 items) and three sample sizes (150, 500, and 1,000 were crossed. Each of the six combinations were replicated 100 times. In addition, power comparisons were made. Results indicated that there were no differences in item and person Rasch fit statistics based on the number of replications. The Type I error rates were close to expected values. It was concluded that the number of replications in Rasch simulation studies are not a major factor influencing fit. Researchers should be more sensitive to the number of persons, number of items, and the correction for degrees of freedom used in the mean square calculation (n vs. n-1). Ten tables are included. (Contains 13 references.) (Author)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Identifiers: Rasch Model; Type I Errors; Weighting (Statistical)
Note: Paper presented at the Annual Meeting of the American Educational Research Association (New Orleans, LA, April 4-8, 1994).