Good Measures from Bad Data

In many assessments, there are examinees who misbehave, and items that are poorly constructed. Nevertheless, everyone must be measured, and every item must be included except those that are obviously, blatantly faulty.

Blatantly faulty items are those that we can show to a content expert (who knows nothing about statistics) and say: "Do you see this ... (typographical error, ambiguity, scoring problem, irrelevant content, ... ). This item is obviously wrong or off-topic!"

Items with conspicuous DIF are more awkward to handle, and depend on the policy of the testing agency. It is easiest to treat them as blatantly faulty and omit them, but they can be split into separate items for separate DIF groups.

But what about random guessing, doubtful items and other problematic data? A three-stage estimation process provides a solution:

i) Analyze all the data. Identify problems.

ii) Reanalyze all the data, but with items and persons with misfit problems deleted and obviously errant or off-target responses omitted. This is the "good" dataset. Save the estimates of the item difficulties and Rasch-Andrich thresholds (for polytomies).

iii) Analyze all the data. Delete only obviously, blatantly faulty items. Anchor (fix) the "good" items at their "good" difficulties, and the polytomies at their "good" thresholds. Output the final set of person measures and item difficulties.

The measure for each person is now estimated in the frame-of-reference of the "good" data with the minimum of distortion of that measure by irrelevant (to that person) "bad" data.

Timed Tests

If we have a timed test, and score all incorrect answers and all item-not-reached answers as "0", then the final items have few correct answers, "1", even if the very last item is the conceptually easiest item on the test.

To get around this problem we do the three-stage analysis. In the second stage, we use only data from examinees who have definitely reached an item (right or wrong). All unreached responses are coded "not administered" (e.g., M for missing) and excluded from the analysis. This analysis gives us the best estimates of the difficulties of the items. We save these "good" item difficulties.

In the third stage, we score all the data 0-1, but use the "good" item difficulties, so that the measures of students who responded to most of the items are not distorted by the performances of students who responded to fewer items.

John M. Linacre

Good Measures from Bad Data, J.M. Linacre ... Rasch Measurement Transactions, 2011, 24:4, 1313

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
Rasch Books and Publications: Winsteps and Facets
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	Appliquer le modèle de Rasch: Défis et pistes de solution (Winsteps) E. Dionne, S. Béland
Introduction to Many-Facet Rasch Measurement (Facets), Thomas Eckes	Rasch Models for Solving Measurement Problems (Facets), George Engelhard, Jr. & Jue Wang	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
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

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/rmt244m.htm

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