The Future of Computer Science (Rasch Measurement?)

Peter Lee, the Managing Director of Microsoft Research Redmond, has made some comments in an interview (Knies, 2011) about the future of Computer Science. These comments also well express the future of Rasch Measurement.

Lee: "The number of potential and real breakthroughs [in computing] waiting to have tremendous impact on people's lives is huge. It has just exploded."

For Rasch, we are still at the waiting stage. We have not yet reached the explosion.

"... advances in machine learning and the manipulation of massive datasets figure to transform the things computers can do and what can be done with them."

Rasch measurement is also being transformed as decision-makers try to make sense of ever larger and more complex databases. The need to impose the conceptual order of unidimensional variables upon chaotic data becomes increasingly pressing.

"...the first decade for such organizations [the great industrial research labs] is all about the ability to recruit great personnel, which leads to a reputation as a legitimate force in the research community."

Though not concentrated in a single organization, the Rasch community at large has, in fact, had 50 years of recruiting great personnel and has cemented its reputation as a legitimate force in the world of research and practice. Might we say that the recruitment and reputation stage peaked around 1990? By that time, the basic array of models, estimation methods, fit assessments, software, and practical examples were in place and moving into routine use.

"The second decade is concerned with growth, among individual researchers and as a lab."

Again, though not involving a single organization, growth in the number of researchers building on the work of the founding innovators has been significant. My recent search on Google Scholar for "Rasch model OR analysis OR scale OR scaling OR measurement" in article titles gives 2,510 hits. Breaking that down by years, 1961-1970 has 10 hits, 1971-1980, 200; 1981-1990, 283; 1991-2000, 496, 2001-2010, 1,160, and 109 articles have come out so far this year. These certainly underestimate the actual numbers of Rasch articles published, as the majority do not include "Rasch" in their titles. Though the numbers here may be only a sample of the actual totals, the growth trend is evident. See also "The Appearance of Rasch in Journal Articles", RMT 24:4, 1311.

"Once a certain critical mass is achieved, then, in the third decade, if the investment has been well-managed and sustained, people begin to turn their sights to a legacy that extends beyond individual fame and respect to a more meaningful impact with the potential to effect a significant societal difference."

Rasch has not yet reached the "third decade". Taking the period to 1990 as the "first decade," does the "second decade" span 1990 to 2000, or 1990 to 2010, or something in between? Though there is great potential for Rasch measurement to effect a significant societal difference, there is very little evidence of many turning their sights in that direction. Various individual articles have touted item banking, adaptive instrument administration, or construct theory as transformative technologies, but none of these explicitly explore a wide range of social impacts.

The time is ripe for such "third decade" explorations. Paraphrasing Peter Lee by replacing "computer-science" with "Rasch measurement" gives us:

"What we in Rasch measurement need is the motivation to break out of a mindset of thinking inwardly about understanding measurement and the mechanisms of measurement and instead look outward to the role of measurement in the world. The success of measurement research is expanding rapidly, but for all of that dramatic progress and expansion, the gap that people see between the progress of measurement science and what society needs from measurement .... People still see that gap not shrinking."

I couldn't have said it better myself. However, all of us in Rasch measurement can go further than what Lee said in response to the last question in the interview. The question was "How, then, can the value of research be measured?"

"We don't do it by dollars. What I ask from managers is to think about impact: 'What high-impact results have you produced? Give me something to brag about. Tell me how you're affecting Microsoft's ... businesses. Tell me how you're contributing to the research community. What is your plan? How are you structuring your team to position itself to make progress?"

Lee rightly eschews financial metrics, instead talking in terms of qualitative indicators of impact, but that's as far as he gets. His response immediately suggests to us that Microsoft needs to construct a latent variable of "research value". Lee has identified some of the item content as well as the "bragging" rating-scale on which items could be scored. Perhaps someone reading this issue of RMT will calibrate a practical quantitative measurement tool for "research value" able to support the decision-making needs of Microsoft and other research-funding agencies.

William P. Fisher, Jr.

Knies R. (2011) 20 Years On, a Future Brighter than Ever. Microsoft Research. research.microsoft.com/en-us/news/features/anniversaryoverview-092611.aspx

The Future of Computer Science (Rasch Measurement?), William P. Fisher, Jr. ... Rasch Measurement Transactions, 2011, 251:2, 1327

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/rmt252e.htm

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