The Rasch Model in Europe: A History

Dr. Gerhard Fischer
Vienna, Austria

25. October 2010

Dear Mr. Purya Baghaei,

Let me answer your request for the history of the Rasch model in Europe.

Erling Andersen was a statistics student of Georg Rasch. He wrote a master's thesis on discrete measurement models with applications to data of social psychology (1966, in Danish), spent a year or so in the USA, then became a coworker of Rasch (as an assistant professor) and, after his doctoral thesis (Conditional Inference for Multiple Choice Questionnaires, 1973, in English) attained a position as senior lecturer (or similar) at the University of Economics in Copenhagen. When Georg Rasch retired, he applied for the vacant chair and was appointed Rasch's successor. Erling Andersen had a very important influence on the spread of knowledge about, and the further development of, the theory of the Rasch Model (RM) owing to his many original articles in international journals and the books he published (for some references to Erling's work, see, e.g., Fischer & Molenaar, 1995, Rasch Models, New York: Springer.) Unfortunately, Erling deceased in 2004.

I came to meet Georg Rasch in 1966 when he was one of the five lecturers at the NUFFIC (Netherland's Universities' Foundation For International Cooperation, sponsored by NATO) summer seminar on Psychological Measurement Theory at The Hague, Netherlands. At that time I had just become assistant professor at the Department of Psychology of the University of Vienna and had no previous knowledge of the RM. I was greatly taken by Georg's new approach to measurement in psychology because it appeared to solve some old fundamental problems of psychology. Apparently Georg noticed my sincere interest, for he invited me to come to Copenhagen for a deeper study of his approach, and he even raised a little money for employing me as his personal amanuensis for a period of two months in 1967. I did not meet Erling at that time in Copenhagen because he was staying in the USA; mostly I had contacts with Georg and with Peter Allerup, another young assistant of Georg, partly also with Jon Stene, a more senior lecturer at the department. (Please note that I am not quite sure about the exact positions of these persons, all the more so as the university system and academic degrees there were different from those in Austria.)

During my stay in Copenhagen, I wrote a computer program for conditional maximum likelihood (CML) estimation of the parameters of the RM, and Peter Allerup helped me to test it at the Nordisc Computer Centre (or similar name; it was a jointly Danish and Swedish closed shop facility). At that time no operational program of that kind was available and the algorithmic/numerical problems seemed all but trivial. One or maybe two years before, Ben Wright had undertaken to write such a program, but his approach to the computation of the elementary symmetric functions was too simplistic, and thus, unsuccessful. As a consequence, the Chicago group around Ben Wright as well as the researchers at ETS claimed that the CML method was "impractical". My algorithm and program were published by myself and Peter Allerup in the book Psychologische Testtheorie (G.H. Fischer, Ed., 1968. Berne: Verlag Huber) which was a proceedings volume of a symposium on test theory I had organized at a conference 1967 in Dusseldorf, Germany. The editing company wanted me to write an introduction to test theory in order to give the book a broader readership, so I wrote a brief exposition of classical test theory, a chapter on a fundamental critique of the classical theory, including of factor analysis, and an introduction to IRT, comprising a derivation of the RM and of the 2PL from their respective sufficient statistics (or raw scores) for the ability parameter. (A minor technical error in the derivation was corrected later in my 1974 book Einführung in die Theorie Psychologischer Tests; Berne: Verlag Huber; in German).

The 1968 proceedings volume had an unexpected effect; obviously many readers had also been subconsciously longing for a better theoretical foundation of quantification in psychology. The computer program was also used a great deal in the following years in the German language countries. An improved and extended set of programs was published in my 1974 book (see above). Both the greatly extended text (606 pages) and the programs were much read and used both in Germany and the Netherlands. Besides myself, my early assistants Hartmann Scheiblechner, who 1972 became professor at the University of Marburg, Germany; Hans Spada, who in 1972 was appointed to a research position at the IPN (an Institute for Science Education associated with the University of Kiel, Germany) and later became professor at the University of Freiburg, Germany; and my early student Wilhelm Kempf, who also became researcher at the IPN and later professor at the University of Konstanz, Germany, contributed a great deal to the understanding and further development of Rasch's approach to measurement in psychology. Our individual and/or joint publications and activities secured for the RM a fixed role both in teaching and research of psychology in Austria and Germany. When Scheiblechner and Spada in 1972 had left Vienna, Klaus Kubinger, now professor at the University of Vienna, and Anton Formann, who eventually became my successor as professor in psychological methodology, were appointed assistants at my department and made their academic career there. Both of them also have contributed much to the development and applications of probabilistic measurement models; Formann particularly specialized in latent class analysis as a generalization of IRT and has published a large number of papers on that topic in many international journals. Tragically, he suddenly perished in summer 2010. (Please note that all these remarks are made from memory and thus may be imprecise in some details or in their dates. The selection of what I mention here is also subjective, of course.) The German, Jürgen Rost, a well-known author in IRT in Germany, was a younger colleague of Spada and Kempf at the IPN at Kiel.

Another person with influence on the spread of the RM in Germany was Hans Christoph Micko, one more Austrian, eventually to become professor at the Technical University of Braunschweig, Germany, who published the multifactorial (or multifacet) generalization of the dichotomous RM already in 1969 and 1970, both in English and German languages (references in Fischer & Molenaar, 1995, see above). This was long before US researchers took interest in that topic. Maybe the first German who delved into the theoretical foundation of the RM was Hans Colonius; he published a very fundamental paper on the scale or measurement issue in the RM in 1979 in German. I think, however, that his primary interest was in mathematical psychology rather than psychometrics.

To me it seems that the first people who became interested in the RM in the Netherlands were (i) Leo van der Kamp, one of the two editors of the NUFFIC seminar proceedings (Leyden University, 1967, mimeographed) and co-editor of the volumes by Dato de Gruijter and Leo van der Kamp (Eds., 1976), Advances in Psychological and Educational Measurement (Proceedings volume of the Second International Symposium on Educational Testing, held in Montreux, Switzerland, 1975; London: J. Wiley) and by Leo van der Kamp, Willem Langerak, and Dato de Gruijter (Eds., 1980), Psychometrics for Educational Debates (Proceedings volume of the Third International Symposium on Educational Testing, held in Leyden, Netherlands, 1977; London: J. Wiley); and (ii) Dato de Gruijter, who also published several journal articles about Rasch modeling, partly in Dutch. Of course there will have been others of whose activities I was just not aware to the same extent.

In the mid seventies (maybe it was 1975) Leo van der Kamp with a group of some 20 younger staff members or graduate students traveled to Vienna to meet with my little psychometric group, and we presented a one-week intensive seminar on our IRT work to them. This apparently triggered interest and research on IRT in the Netherlands. In 1977 and 1978 I was invited to teach similar seminars at the Universities of Nijmegen, Groningen, and Twente (Enschede), all in the Netherlands. Again, the audiences were staff members and graduate students. At that time, the interest in IRT was growing fast in the Netherlands, and they were very interested in knowing about our research in Vienna. In subsequent years it was mainly at CITO (Arnhem; Norman Verhelst and Cees Glas), at the University of Twente (Enschede; Wim van der Linden), at the University of Groningen (Ivo Molenaar), at the University of Utrecht (Gideon Mellenbergh), and in part at the University of Nijmegen (Eddie Roskam) where the RM and related models were studied and further developed. (Again, this is just a personal recollection and may be quite incomplete.) Anyway, our colleagues and friends in the Netherlands were then catching up very fast and soon took the lead in IRT in Europe. As I have often experienced, their resources were far superior to ours in Vienna, so that it was impossible for us to keep pace with them.

If you want to know more about references to early work on the RM and/or on my personal views on the RM-related models, see the 1995 (2nd revised printing 1998) volume by Fischer & Molenaar, Rasch Models; New York: Springer-Verlag. More recently I have given a concise account of my views, including some of my later research, in the chapter "Rasch Models" in the volume of Rao & Sinharay (Eds., 2007), Psychometrics. Handbook of Statistics, Vol .26; Amsterdam: Elsevier.

I hope these remarks are useful for you, but please do not hold me responsible for the correctness of all details and for completeness. When I quit the Department of Psychology upon retirement in 1999, I sat on a huge amount of material after 39 years of academic work. I was neither able nor willing to take all this home. So I dumped most of it, including the documents concerning most seminars, conferences, presentations, travels, etc. Therefore, I cannot easily reconstruct exactly in what years I have been here or there. Moreover, I apologize if I am overlooking or just not mentioning persons of equal importance in the early European IRT work.

Best regards,

Gerhard Fischer

The Rasch Model in Europe: A History, G.H. Fischer ... Rasch Measurement Transactions, 2010, 24:3 p. 1294-5

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/rmt243d.htm

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