Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Date of Graduation
Doctor of Philosophy (PhD)
Department of Graduate Psychology
Brian C. Leventhal
The Rasch model is commonly used to calibrate multiple choice items. However, the sample sizes needed to estimate the Rasch model can be difficult to attain (e.g., consider a small testing company trying to pretest new items). With small sample sizes, auxiliary information besides the item responses may improve estimation of the item parameters. The purpose of this study was to determine if incorporating item property information (i.e., characteristics of the items related to item difficulty) in a random effects linear logistic test model (RE-LLTM) would improve estimation of item difficulty. A simulation study was conducted that varied sample size, number of items, distribution of the item easiness parameters, percentage of variance explained by the item properties, type of item property, and treatment of the fixed effects slopes. Results showed that in certain circumstances (i.e., long tests with small sample sizes), the inclusion of item properties improved estimation of the item difficulties. Results for other parameters in the model are also discussed.
Sauder, Derek, "Can auxiliary information improve Rasch estimation at small sample sizes?" (2020). Dissertations, 2020-current. 23.