The purpose of this study was to apply a random item mixture nominal item response model (RIM-MixNRM) for investigating instruction effects. The host study design was a pre-test-and-post-test, school-based cluster randomized trial. A RIM-MixNRM was used to identify students' error patterns in mathematics at the pre-test and the post-test. Instruction effects were investigated in terms of students' transitioning in error patterns. That is, we compared students' error patterns in the Enhanced Anchored Instruction (EAI) condition with students' error patterns in a business-as-usual (BAU) instructional condition following each instruction. We also compared error patterns of students with math disabilities and students without math disabilities following the two types of instruction. [This paper was published in: L. A. van der Ark, D. M. Bolt, W.-C. Wang, J. A. Douglas, M. Wiberg (Eds.), "Quantitative Psychology Research: The 80th Annual Meeting of the Psychometric Society, Beijing, 2015" (pp. 39-48). Proceedings in Mathematics & Statistics 167. Cham, Switzerland: Springer International Publishing.]