Item Discrimination, Test Optimization and W. E. Deming

Take a look at the most discriminating item on your Test. This item operationalizes your best effort at separating your high performers from your low performers. From the perspective of this item, the distance on the latent variable between the high and low performers is greater than it is for any other item in your Test. Wonderful!?

Statistician William Edwards Deming observed this type of optimization in many industrial processes. Here is a composite of some of his examples: Several machine tools were manufacturing the same component. Different operators employed different tactics for maximizing usable output. Consequently, some of those machine tools were set to tighter tolerances than specified, in order to minimize out-of-"official"-tolerance components. Some operators set their machines within "official" tolerance limits, but deliberately made components toward the larger end of the tolerance interval, so that components could be easily remachined smaller if discovered to be out of tolerance. In fact, every manufactured component represented a personal "best effort" by a machine-tool operator. But W. E. Deming perceived that "We are being ruined by our best efforts" (Neave, 1992).

Optimizing each part does not necessarily optimize the whole. For instance, separately optimizing the performance of each member of a basketball team may not optimize team performance. Separately optimizing each component of an audio amplifier may not optimize audio output quality, indeed with some designs may worsen it. Separately optimizing the skills of each musician may not make the orchestra perform better.

The problem with "best efforts" is that they tend to focus on the immediate situation, ignoring the larger context. Those machine operators were given the specifications for the part they were producing, but had no idea how each of their individual approaches impacted the overall quality of the final product. In fact, the highest quality final product was produced by using the widest allowable tolerance range (which was wider than the overly-cautious design engineers originally specified), and setting the machine tool to work in the center of it. This also reduced rejection rates, remachining and improved component interchangeability.

The same is true of Test items. Allowing excessive variation in item discrimination may optimize individual items, but that variation degrades the meaning and utility of the Test as a whole. So how do we know when an optimizing tactic will work? "Only theory can help us figure out what's right and what's wrong" - Deming again. The Rasch model tells us to aim at the center of the discrimination range, and permits us some, but not too much, variation (RMT 14:3, 743).

Neave H.R. (1992) The Deming Dimension. Knoxville, TN: SPC Press.

Item Discrimination, Test Optimization and W. E. Deming … Rasch Measurement Transactions, 2005, 18:4 p. 9

Rasch Books and Publications
Invariant Measurement: Using Rasch Models in the Social, Behavioral, and Health Sciences, 2nd Edn. George Engelhard, Jr. & Jue Wang	Applying the Rasch Model (Winsteps, Facets) 4th Ed., Bond, Yan, Heene	Advances in Rasch Analyses in the Human Sciences (Winsteps, Facets) 1st Ed., Boone, Staver	Advances in Applications of Rasch Measurement in Science Education, X. Liu & W. J. Boone	Rasch Analysis in the Human Sciences (Winsteps) Boone, Staver, Yale
Introduction to Many-Facet Rasch Measurement (Facets), Thomas Eckes	Statistical Analyses for Language Testers (Facets), Rita Green	Invariant Measurement with Raters and Rating Scales: Rasch Models for Rater-Mediated Assessments (Facets), George Engelhard, Jr. & Stefanie Wind	Aplicação do Modelo de Rasch (Português), de Bond, Trevor G., Fox, Christine M	Appliquer le modèle de Rasch: Défis et pistes de solution (Winsteps) E. Dionne, S. Béland
Exploring Rating Scale Functioning for Survey Research (R, Facets), Stefanie Wind	Rasch Measurement: Applications, Khine	Winsteps Tutorials - free Facets Tutorials - free	Many-Facet Rasch Measurement (Facets) - free, J.M. Linacre	Fairness, Justice and Language Assessment (Winsteps, Facets), McNamara, Knoch, Fan
Other Rasch-Related Resources: Rasch Measurement YouTube Channel
Rasch Measurement Transactions & Rasch Measurement research papers - free	An Introduction to the Rasch Model with Examples in R (eRm, etc.), Debelak, Strobl, Zeigenfuse	Rasch Measurement Theory Analysis in R, Wind, Hua	Applying the Rasch Model in Social Sciences Using R, Lamprianou	El modelo métrico de Rasch: Fundamentación, implementación e interpretación de la medida en ciencias sociales (Spanish Edition), Manuel González-Montesinos M.
Rasch Models: Foundations, Recent Developments, and Applications, Fischer & Molenaar	Probabilistic Models for Some Intelligence and Attainment Tests, Georg Rasch	Rasch Models for Measurement, David Andrich	Constructing Measures, Mark Wilson	Best Test Design - free, Wright & Stone Rating Scale Analysis - free, Wright & Masters
Virtual Standard Setting: Setting Cut Scores, Charalambos Kollias	Diseño de Mejores Pruebas - free, Spanish Best Test Design	A Course in Rasch Measurement Theory, Andrich, Marais	Rasch Models in Health, Christensen, Kreiner, Mesba	Multivariate and Mixture Distribution Rasch Models, von Davier, Carstensen

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/rmt184g.htm

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