From a taped interview with Professor Georg Rasch carried out by David Andrich - May 1979 at Rasch's thatched cottage on the Danish island of Laesoe.
DA: Georg, how did you get directed into mathematics?
GR: I happened to get a very good teacher in arithmetic and the kind of algebra that is quite close to arithmetic, that is elementary algebra. My teacher, Mr. Lehn, clearly realized that I was a mathematician.
Then, Mr. Lehn said to my father, your son is a gifted mathematician, you must take care that he gets in a secondary school where he does learn some proper mathematics. That was my good fortune.
DA: When did you begin your research studies?
GR: I did research already while a student. My old teacher, Lehn, was quite right when he declared that the son of Mr. Rasch [a Lutheran minister] was a born mathematician. Not one of the best ones in the world, by no means, but the interest in mathematics and the need for making research in mathematics has followed me from very early days until my untimely death may come [too soon in 1980]. So this is one point I want to stress: that, although I have been most known as a statistician, my original training and my original gift is in mathematics.
DA: You were doing some statistical consulting at the Hygienic Institute and two academics, Nørlund [Professor of Mathematics at the University of Copenhagen] and Madsen [Director of the Serum Institute], knew about this. How did they help you?
GR: They agreed that it was very fine that Dr. Rasch would do a job there, but that he needed a proper education in the latest developments of statistics. One of them, I don't know which one, knew about R. A. Fisher. Then these two applied to the Rockefeller Foundation for a year's study for me with R. A. Fisher in London [at the Galton Laboratory].
DA: What year was that?
GR: I went over there in September  and stayed there a full year. I learned quite a lot there. Of course, I went through his statistical methods and learned the kind of chi-squares and so on that he used, and also, of course, the maximum likelihood method. But what caught my interest most was not that, but what he said, namely that this is a form of generalization of just the same thing as Gauss did when he invented the method of least squares. The method of least squares is not, in Fisher's interpretation, just a minimization of the sum of squares. It is the maximization of the probability of the observations, choosing such values as estimates of the parameters that will maximize the probability of the set of observations you have at your disposal. There is a very essential difference from just minimizing a sum of squares. That philosophy went further on when he got to the concept of sufficiency that, I think, is really the high mark of what he ever did. Many may consider it just a mathematical trick, but I think it's much more than that. I feel, that this is most important thing I got from Fisher.
Fisher was a remarkable mathematician. He was remarkable in being able to look right through a lot of mathematical dust and see the essentials of it.
Now in my language today, the sufficiency concept is very remarkable. It plays an enormous role, as we shall see a bit later on, in the probabilistic theory for specific objectivity.
DA: Tell us about the development of the dichotomous model.
GR: The discovery of that model actually was an achievement in connection with my work in 1952 in the analysis of the reading tests and the study of the multiplicative Poisson models. I chose the multiplicative Poisson because it seemed a good idea mathematically, if it would work. It turned out that it did work. Then I wanted to have some good motivation for using it and not only the excuse that statistically it worked perfectly. I wanted to have a good reason for trying that after I had used it.
The probabilities for the dichotomous case should therefore be of the form /(1+) and then the would have to have a factor that was personal through all of the (what we might call) items, and each item, of course, would have a parameter, and then I have my proof.
I should say that about 1957, I gave to those who wanted to listen to it, some free lectures on the researches I had done since the construction of the new intelligence tests. I told about both the multiplicative Poisson and I told about this small nice model which sorts items out from each other.
DA: What set you thinking along the lines that lead to the concept of specific objectivity.
GR: What set me thinking was [Nobel-Prize-winning Economist Ragnar] Frisch's surprise that the famous parameter was eliminated. Then a couple of days later, I asked myself on a Sunday morning, half awake, which kind of models have that in common with the multiplicative Poisson model, which was the one I had used to demonstrate the matter to Ragnar Frisch. That is, which kinds of models have that property in common with the multiplicative Poisson model that one set of parameters can be eliminated while dealing with another set.
DA: What happened in Chicago in 1960?
GR: I lectured on the contents of my book [Probabilistic Models.]. Jimmy Savage [Professor of Statistics] started to listen to some of it, but, of course, the mathematical details were so well-known to him. So in the long run, he got tired of it. I did not blame him. So did most of the audience. Only Ben [Wright] stayed on. He was regular, took his notes, and I discussed data he brought with him. I also disclosed to him the generalization that Frisch had inspired me to make and the points I was to present at Berkeley [Fourth Symposium on Mathematical Statistics and Probability].
DA: Your health has not been so good lately?
GR: Just around December last year  I got extremely sick again with a heart attack. A perfectly ridiculous struggle between a generally good constitution and an old and weak heart. So far I have conquered the heart. I have been recovering from that. I am not as strong as I was before this, but anyhow the mental part seems to be working. Your coming [from Australia] has been a very great inspiration to me, David, so I am very grateful that you would spend four, five days of the period you have at your disposal as our guest and in discussions with me.
The original tape recorded conversation was replayed at IOMW9, March 1997, University of Chicago.
Georg Rasch in His Own Words. Andrich D. A. Rasch Measurement Transactions, 1997, 11:1 p. 542-3.
|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.
|Coming Rasch-related Events|
|Jan. 25 - March 8, 2023, Wed..-Wed.||On-line course: Introductory Rasch Analysis (M. Horton, RUMM2030), medicinehealth.leeds.ac.uk|
|Apr. 11-12, 2023, Tue.-Wed.||International Objective Measurement Workshop (IOMW) 2023, Chicago, IL. iomw.net|
|June 23 - July 21, 2023, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Further Topics (E. Smith, Winsteps), www.statistics.com|
|Aug. 11 - Sept. 8, 2023, Fri.-Fri.||On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets), www.statistics.com|
The URL of this page is www.rasch.org/rmt/rmt111d.htm