Survey Analysis and Rasch

The Michigan Department of Education and Employability Skills Task Force distribute a survey designed to identify the critical skills, behaviors and attitudes employers want in employees. Respondents rate 86 items as critical, highly needed, somewhat needed or not needed. In 1989, Michigan public school principals asked elementary and secondary teachers to fill out this survey.

Conventional survey analysis depends on insupportable assumptions about the numerical values of response categories. An interval scale must be specified on which critical might be valued at, say, 4, highly needed at 3, somewhat needed at 2, and not needed at 1. But there is no objective basis for assigning or means of confirming any particular choice of values. Rasch analysis requires only that response categories are coded in a qualitatively increasing order. The working "values" of the responses are estimated from the data. This reflects the views of the survey respondents more accurately than the conventional method.

The Rasch step calibrations for the teachers were:

       STEP TO               SECONDARY  ELEMENTARY
  not needed                    N/A        N/A
  somewhat needed               -.92      -1.03
  highly needed                 -.72       -.47
  critical                      1.64       1.50

This shows that these teachers regarded the steps from not needed to somewhat needed and from somewhat needed to highly needed as closer in value than the final step to critical. The region along the continuum in which the response somewhat needed stood out was so brief that little information was conveyed by the use of that category. In general, skills were either not needed, highly needed, or critical.

Conventionally, misfitting items are those with high raw response standard deviations. Rasch misfitting items are those for which no clear "latent scale" has been manifested. These contrasting types of misfit affected much the same items for secondary school teachers, but totally different items for elementary teachers demonstrating that Rasch misfit is not necessarily identical to conventional misfit. The Rasch analysis provided the more useful interpretation.

Survey Analysis and Rasch, William L. Brown … Rasch Measurement Transactions, 1990, 4:2 p.106

Rasch Publications
Rasch Measurement Transactions (free, online)	Rasch Measurement research papers (free, online)	Probabilistic Models for Some Intelligence and Attainment Tests, Georg Rasch	Applying the Rasch Model 3rd. Ed., Bond & Fox	Best Test Design, Wright & Stone
Rating Scale Analysis, Wright & Masters	Introduction to Rasch Measurement, E. Smith & R. Smith	Introduction to Many-Facet Rasch Measurement, Thomas Eckes	Invariant Measurement: Using Rasch Models in the Social, Behavioral, and Health Sciences, George Engelhard, Jr.	Statistical Analyses for Language Testers, Rita Green
Rasch Models: Foundations, Recent Developments, and Applications, Fischer & Molenaar	Journal of Applied Measurement	Rasch models for measurement, David Andrich	Constructing Measures, Mark Wilson	Rasch Analysis in the Human Sciences, Boone, Stave, Yale
in Spanish:	Análisis de Rasch para todos, Agustín Tristán		Mediciones, Posicionamientos y Diagnósticos Competitivos, Juan Ramón Oreja Rodríguez

Forum

Rasch Measurement Forum to discuss any Rasch-related topic

Go to Top of Page
Go to index of all Rasch Measurement Transactions
AERA members: Join the Rasch Measurement SIG and receive the printed version of RMT
Some back issues of RMT are available as bound volumes
Subscribe to Journal of Applied Measurement

Go to Institute for Objective Measurement Home Page. The Rasch Measurement SIG (AERA) thanks the Institute for Objective Measurement for inviting the publication of Rasch Measurement Transactions on the Institute's website, www.rasch.org.

The URL of this page is www.rasch.org/rmt/rmt42d.htm

Website: www.rasch.org/rmt/contents.htm