"What we need, if our appraisals [of alternative theories] are to be at all reliable, is serious historical scholarship devoted to the various research traditions in any given field of inquiry" (Laudan, 1977, p. 194).
A variety of measurement theories have been proposed for quantifying human characteristics during the 20th century. They range from one major theory with minor variations (Goldstein & Wood, 1989) to "a growing (and bewildering) array of models" (Thissen & Steinberg, 1986, p.567). Given this variety, how can we organize our thoughts about relevant criteria for comparing different models for quantifying such human characteristics as cognitive ability, mathematics achievement and self concept?
One answer, the approach I use to guide my work on the history and philosophy of measurement, is the idea of "research traditions" developed by Laudan (1977). Recent research on the history and philosophy of science has used this idea to trace progress in different physical and social sciences (Laudan, 1977; Donovan, Laudan & Laudan, 1988). Research traditions are similar to paradigms (Kuhn, 1970), research programs (Lakatos, 1978) and disciplines (Cronbach, 1957, 1975). This concept can provide a useful framework for examining progress in measurement theory during the 20th century. A research tradition has the following characteristics: (1) it defines the aspects of quantification which are viewed as problematic, (2) it defines the methods which can be used to address these problems, and finally, (3) through the definition of measurement problems and methods, a research tradition has a significant impact on how social science research is conducted. Different research traditions imply different assumptions and different ways of viewing measurement and social science research. The problems selected for study, the statistical models used to analyze the data, the results of the inquiry and the policy implications drawn from the research depend on the measurement models used.
In measurement, there are two research traditions. One is a scaling tradition. The other is a test score tradition. The scaling tradition focuses on the calibration of individual items and the measurement of persons on a shared latent variable. The roots of this scaling tradition are in psychophysics with E. L. Thorndike, Thurstone, Guttman, Lazarsfeld and Rasch, the major contributors. The test score tradition focuses on total test scores, and the linear decomposition of these scores into true scores and error components. The original work was initiated by Spearman (1904) [who originated the psychometric use of the term "reliability"]. Two current approaches to measurement theory in the test score tradition involve the application of analysis of variance procedures by Cronbach and his colleagues (1963, 1972), and the use of factor analysis to provide a framework for addressing measurement issues related to reliability and validity (Joreskog, 1971, 1979).
A central task in the history of measurement theory is to examine progress. The evaluation of how far we have come towards the solution of key empirical and conceptual problems in educational and psychological measurement is a comparative process. The concept of research traditions can play an important role in structuring our thoughts about progress in measurement theory. Three major steps in this evaluation are (1) development of criteria for comparing theories, (2) identification of major theories, and (3) comparison of theories based on these criteria.
I am applying this approach to one of the basic puzzles in the history of measurement theory: why did the test score tradition become the dominant tradition in the practice of educational and psychological testing? Thorndike's work at the beginning of the 20th century is clearly in the scaling tradition. Strong arguments can be made for considering him the father of item response theory. Yet even his own student, Ben Wood, ended up aligned with the test score tradition. Thurstone's work on absolute scaling was certainly familiar to all measurement theorists. Yet our research publications are still more likely to report KR20's and alpha coefficients than calibrated items on maps of variables of the kind used by Thurstone in the 1920's. Andrich (1988) provides an analysis of how advances in Rasch measurement represent a paradigm shift in social science measurement and this may provide part of the answer to the question. And yet, at the turn of the century and certainly until WWI, it seems that either research tradition could have become dominant. If you have any thoughts about why the test score tradition become dominant, I would like to hear your ideas.
Research Traditions and History of Measurement, G Engelhard Jr Rasch Measurement Transactions, 1991, 4:4 p. 126
Please help with Standard Dataset 4: Andrich Rating Scale Model
|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|
|Sept. 15-16, 2017, Fri.-Sat.||IOMC 2017: International Outcome Measurement Conference, Chicago, jampress.org/iomc2017.htm|
|Oct. 13 - Nov. 10, 2017, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|Oct. 25-27, 2017, Wed.-Fri.||In-person workshop: Applying the Rasch Model hands-on introductory workshop, Melbourne, Australia (T. Bond, B&FSteps), Announcement|
|Jan. 5 - Feb. 2, 2018, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|Jan. 10-16, 2018, Wed.-Tues.||In-person workshop: Advanced Course in Rasch Measurement Theory and the application of RUMM2030, Perth, Australia (D. Andrich), Announcement|
|Jan. 17-19, 2018, Wed.-Fri.||Rasch Conference: Seventh International Conference on Probabilistic Models for Measurement, Matilda Bay Club, Perth, Australia, Website|
|April 13-17, 2018, Fri.-Tues.||AERA, New York, NY, www.aera.net|
|May 25 - June 22, 2018, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|June 29 - July 27, 2018, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Further Topics (E. Smith, Winsteps), www.statistics.com|
|Aug. 10 - Sept. 7, 2018, Fri.-Fri.||On-line workshop: Many-Facet Rasch Measurement (E. Smith, Facets), www.statistics.com|
|Oct. 12 - Nov. 9, 2018, Fri.-Fri.||On-line workshop: Practical Rasch Measurement - Core Topics (E. Smith, Winsteps), www.statistics.com|
|The HTML to add "Coming Rasch-related Events" to your webpage is:|
The URL of this page is www.rasch.org/rmt/rmt44d.htm