Fits about "Misfit"

One impediment to acceptance of the Rasch model as a viable method of measurement in psychology and education has been the concept of fit.

Fit implies meeting requirements or matching intentions. The concept is well accepted in the everyday and the physical science worlds. When a tape measure appears stretched, it is rejected and another found. When one wishes to measure the circumference of a cylinder, one seeks a measuring instrument pertinent to the job. We use micrometers to measure small distances, pedometers and transcepts to measure large. The concept of fit is well known to statisticians. Tests of fit are powerful tools which enable statisticians to make objective, yet qualified inferences. It is normal practice to match the measured and the measure.

But when it comes to using the Rasch model as a method of measurement, the concept of fit is not accepted. "How dare we reject some items or some persons? One must never tamper with the test. That is manipulating data which is not acceptable." Maybe "one" should take a second look.

The Rasch model is stochastic. It asserts that the data depend on probability, not certainty. When an event has a high probability, that does not mean it will definitely take place. We are, nevertheless, surprised when highly probable events persist in not occurring. The concept of fit is a natural consequence of any stochastic model. It specifies an indication of the match between a group of persons and a set of items. If for any reason a few persons from the group or a few items from the set do not perform as expected, these will be flagged as persons or items differing from expectation and therefore misfitting. Fit indicates the validity of the item calibrations and the person measures. Far from being unacceptable, fit is the essential gauge of the performance validity of the test content/construct in the circumstances in which it is used.

The Rasch model is a useful idealization of reality. Some misfit is to be expected. We know from practical experience that person raw scores do not exhibit invariance. The stochastic Rasch model actually fits our own expectations very well. Do not reject this useful model on a misunderstanding of intention.

Fits about "Misfit", F Shaw … Rasch Measurement Transactions, 1991, 5:1 p. 132

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/rmt51g.htm

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