Byrum, Denmark Oct 13th, 1978
Dear Ben [Wright]:
As you presumably already know and anyhow will realize from the enclosed [correspondence], I have indeed cooled down to acquiescing to a reprinting of Prob. Mod. - such as it is! (possibly after some misprints and the like have been removed).
Which does not mean that today I am satisfied with the book. On the contrary, already years ago I played with the idea of rewriting it completely in view of the developments both as regards access to electronic facilities and as regards the theoretical foundation, since 1960.
However, lecturing in Australia, on what I knew by then, and at the same time receiving from my young friend Kare Borchsenius very advanced contributions to the theory of specific objectivity, convinced me that my primary obligation for the next few years must be to concentrating upon the specific objectivity, clarifying its foundations and demonstrating how it lies at the bottom of general statements with well-defined fields of validity. - In which connection I may have to return to the weakest part of the book, viz., Chs. VI [Control of the model] and VII [Notions implied in the structural model for items].
But even if a revision of these chapters - and, in fact, some more sections - are indeed desirable, I don't think that Ch. VI will do much harm, because nobody will use its technique [Rasch's emphasis] any more = to somebody it may even turn out to be a challenge to establishing as detailed and effective model controls on a theoretically firm basis.
Ch. VII is a different and deeper problem. Its real limitation lies in starting from a pretending that it is known what "measuring" is, not only of accelerations - which are the reactions to be observed -but also of mass and force which in fact should be derived from the structure of the reactions. That such derived measures might have to be confronted with directly defined measures of mass and force is a further complication that presumably would require supplementary (thought-) experiments.
All of which I did not realize in 1960 - neither did Maxwell in 1876, nor did Newton some 200 years earlier.
So far, so bad, as regards what I attempted to do in Ch. VII. But today the situation has changed to the worse: even direct measurement leaves a lot to be desired as regards its conceptual clarity. That this is so, is a rather recent discovery of where the usual axioms of measurement come from. That current theory of measurement looks like the mathematics of real numbers may be very convenient, but if that were a necessity, then it should be derived from something more serious than a pure analogy. And in particular the attempts at generalizing to multidimensional measurement so far have seemed to end up with purely mathematical ingenuity, without any necessity.
What to do then? Well, the theory already developed for comparing objects with specific objectivity with a framework where the objects react to contacting a set of agents can be applied directly to a situation where the set of agents is the same as the set of objects, thus providing for objects being "compared" by means of contacts with other objects, that, I think, is what lies at the bottom of "direct measurement". [See paired comparisons, RMT 9:2 p.425].
Realizing this is, however, so recent a discovery to me that you will not even find it in the reprint [Danish Philosophical Yearbook, 1977] that I am anxious to send you, but it can in fact be derived from it.
My reason for at all mentioning this matter here is to make clear that even a revision of Ch. VII would not be feasible within the framework on which the whole book has been built up.
And this is my final argument for leaving the book as it is!
"G. Rasch's Probabilistic Models.. book represents an attempt to
create new paths for scientific behavioral statistics which, till now, have confused
groups with individuals... We encourage as many people as possible to obtain and
read the book."
from a 1962 review by Sven Rydberg, University of Stockholm, Nordisk Psykologi, 14(7), p.347-8.
Georg Rasch reviews "Probabilistic Models". Rasch G. Rasch Measurement Transactions, 1995, 9:2 p.424
|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|
|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/rmt92c.htm