Investigating the application of Rasch Theory in measuring change in middle school student performance in physical science.

  • Cunningham J
  • 1


    Mendeley users who have this article in their library.
  • N/A


    Citations of this article.


Newton's Universe (NU), an innovative teacher training program, strives to obtain measures from rural, middle school science teachers and their students to determine the impact of its distance learning course on understanding of temperature. No consensus exists on the most appropriate and useful method of analysis to measure change in psychological constructs over time. Several item response theory (IRT) models have been deemed useful in measuring change, which makes the choice of an IRT model not obvious. The appropriateness and utility of each model, including a comparison to a traditional analysis of variance approach, was investigated using middle school science student performance on an assessment over an instructional period. Predetermined criteria were outlined to guide model selection based on several factors including research questions, data properties, and meaningful interpretations to determine the most appropriate model for this study. All methods employed in this study reiterated one common interpretation of the data – specifically, that the students of teachers with any NU course experience had significantly greater gains in performance over the instructional period. However, clear distinctions were made between an analysis of variance and the racked and stacked analysis using the Rasch model. Although limited research exists examining the usefulness of the Rasch model in measuring change in understanding over time, this study applied these methods and detailed plausible implications for data-driven decisions based upon results for NU and others. Being mindful of the advantages and usefulness of each method of analysis may help others make informed decisions about choosing an appropriate model to depict changes to evaluate other programs. Results may encourage other researchers to consider the meaningfulness of using IRT for this purpose. Results have implications for data-driven decisions for future professional development courses, in science education and other disciplines. (PsycINFO Database Record (c) 2016 APA, all rights reserved)

Author-supplied keywords

  • 0450:Middle School education
  • 0530:Teacher education
  • 0714:Science education
  • Academic Achievement
  • Academic achievement
  • Change in performance
  • Education
  • Item Response Theory
  • Item response
  • Middle School Students
  • Middle School education
  • Middle Schools
  • Middle school students
  • Newton's Universe
  • Physical science
  • Professional Development
  • Racking and stacking
  • Rasch Theory application
  • Rasch model
  • Science Education
  • Science education
  • Teacher Education
  • Teacher education
  • Teacher training
  • Teachers
  • Theory
  • measuring change
  • middle school student performance
  • physical science
  • teacher training program

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


  • Jessica D Cunningham

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free