Introduction to Georg Rasch's 1972 Retirement Lecture

Please remember, as you read our translation of Georg Rasch's "Objectivity in Social Sciences. A Method Problem" on page 1252 of this RMT that this is Rasch's manuscript for his Retirement Lecture and probably not a formal Journal paper. The language is at points obscure, and there are a few trivial errors (e.g., in the analysis of the data in Table 5) that were corrected when Rasch gave his lecture and would have been corrected if Rasch had taken the time to rewrite it as a paper. During the translation of the manuscript into English, we have been tempted to correct the errors and improve the language. We have (almost) not succumbed to the temptation, assuming that the reader prefers the pure Rasch version despite its shortcomings and will be able to read "between the lines" where that is required.

The paper itself is interesting for many reasons. Today, the majority of researchers using Rasch models remember him primarily for his contributions to objective measurement. The Retirement Lecture shows you Georg Rasch the statistician as Danish statisticians of the time remember him. The lecture mentions the Rasch model for dichotomous items in passing but is more concerned with situations requiring comparison of groups rather than persons and there is no discussion of measurements as such. The notion of specific objectivity was very important to Rasch. In the lecture, specific objectivity is a methodological rather than a measurement issue. As always, the frames of reference contain agents, objects and reactions, but the reactions depending on these are probabilities, not outcomes on stochastic variables. Given this set-up, Rasch talks about specific-objective estimation of parameters in probabilistic (and therefore statistical) models.

In Sections 2-10 Rasch revisits the deterministic case and Newton's Second Law. He was just setting the scene here, and there is probably nothing new to those who are well versed in the theory of Rasch models.

Section 11 uses the deterministic framework for a discussion of the dependence of production on capital and labour. This is the weakest part of the manuscript since it is a purely academic exercise with no data. My guess is that the only reason why this was included was that he was criticised (with considerable justification) for not having done anything for econometrics and economic statistics during his years as Professor at the Dept. of Statistics at the Institute of Economics.

Sections 12-15 are to me the most interesting sections. Here he discusses the logistic regression model and shows that specificly objective estimation of the parameters of such models is feasible. He never uses the term "logistic regression", and I remember thinking that he was "just" reinventing an already existing model when I heard him give this lecture. Rereading the manuscript after all these years, I can see that the point of the paper is that he discusses what we today would refer to as conditional logistic regression, pointing out that specific-objective estimation requires conditional logistic regression.

In the remaining sections, Rasch discusses the possibilities of extending the static frames of reference to dynamic frames and stochastic processes, and discusses data on development of wages over time and longitudinal data on mortality rates. Extending the frames of reference in this way was very important to Rasch and it was one of the issues that he intended to pursue in his years as Professor Emeritus. The Sections read more as an illustration of the problem and a statement of intent than anything else. Comparing these sections to the section on dynamic models in his 1977 paper on specific objectivity reveals that in this one respect he was perhaps less than successful, but it is still of interest to see what he was thinking about.

Svend Kreiner

June, 2010

Rasch, G. (1977). Specific Objectivity: An Attempt at Formalizing the Request for Generality and Validity of Scientific Statements. See www.rasch.org/memo18.htm

Introduction to Georg Rasch's 1972 Retirement Lecture, S. Kreiner ... Rasch Measurement Transactions, 2010, 24:1 p. 1243

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/rmt241a.htm

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