"The major scientific disadvantage of [significance testing and confidence intervals] is that their significance is merely an inference derived from principles of mathematical probability, not an evaluation of substantive importance for the big or small magnitude of the observed distinction. ... They offer no guidance for the basic quantitative scientific appraisals that depend on purely descriptive rather than inferential boundaries. ... The latter evaluation has not received adequate attention during the emphasis on probabilistic decisions; and careful principles have not been developed either for the substantive reasoning, or for setting appropriate boundaries, for big or small. After a century of significance inferred exclusively from probabilities, a basic scientific challenge is to develop methods for deciding what is substantively impressive or trivial."
Feinstein, A. R. (1998). P-values and confidence intervals: Two sides of the same unsatisfactory coin. Journal of Clinical Epidemiology, 51(4), 355-60.
Courtesy of William P. Fisher
"Measurement can belong, therefore, only to that which is objective and spacial, and the psycho-physical quanta must stand for the physiological elements of our reactions, expressed in personal equations."
George Herbert Mead. "The Problem of Psychological Measurement", Proc. of the American Psychological Association, New York: MacMillan & Co. (1894): 22-23.
Science consists of two general areas: there is the act of measurement, which is the empirical side of science, and there is the development of mechanisms, which is its theoretical side.
Dr. Dean Radin on "Closer to Truth", PBS, 2000
The Cambridge Assessment Network hosted the 2nd meeting of the UK Rasch Users' Group at Hughes Hall in Cambridge, England on Monday 5th February 2007. The purpose of the group is to provide a forum for Rasch practitioners in the UK working in different fields to get together to share ideas and present research.
The 38 delegates heard presentations covering a wide range of practical applications of Rasch measurement - from investigating misfit in classroom mathematics tests to measuring rehabilitation outcomes in brain-injured patients. During the lunch break there were demonstrations of developments from Cambridge ESOL in item banking, item analysis and computer adaptive testing, and of Cambridge Assessment's TSA (Thinking Skills Assessment) online test for university admissions.
The program for the day, and the abstracts and slides for the presentations will soon be available at www.assessnet.org.uk/mod/resource/view.php?id=142
Tom Bramley
Assistant Director, Research Division
Assessment Research & Development
Cambridge Assessment
1 Regent Street, Cambridge, CB2 1GG
Direct Dial: 01223 553985
www.cambridgeassessment.org.uk
MetaMetrics Workshop Series on Psychometrics
An Introduction to Rasch Measurement: Theory and Application
by David Andrich
March 26-29, 2007 - Monday-Friday
Durham , North Carolina
You are invited to a free four-day workshop introducing the theory and applications of Rasch measurement and providing hands-on experience with RUMM2020 data analysis software. The workshop will combine lecture, question-and-answer and small-group instruction. You will have opportunities to analyze your own data.
We will study principles of the Rasch models from the perspective of the Item Characteristic Curve and Differential Item Functioning. RUMM2020 will be used to demonstrate concepts and teach you how to analyze data in a flexible way. Case studies will be used that bring together the professional understanding of the variable of assessment, item construction, and the use of statistical indices in determining the validity of item sets.
Instructional material will apply Rasch models to dichotomous (multiple choice) and polytomous (rating scale and partial credit) data. Familiarity with Microsoft Excel, basic statistics and the Windows platform is a plus.
More information and registration details at:
http://www.lexile.com/DesktopDefault.aspx?view=re&tabindex=3&tabid=92
Rasch Workshop
Hands-on Introduction to
IRT/Rasch Measurement Using Winsteps
by Ken Conrad & Barth Riley
March 26-27, 2007 - Monday-Tuesday
University of Illinois - Chicago
Social scientists have great need for the development of valid measures, e.g., of the quantity and quality of health services and of the outcomes of those services. Many researchers are frustrated when existing instruments are not well tailored to the task, since they then cannot expect sensitive, accurate, or valid findings. This workshop presents the theory and practice of classical test theory, the traditional approach. It then provides an overview of modern measurement as practiced using item response theory with a focus on Rasch measurement. Rasch analysis provides the social sciences with the kind of measurement that characterizes the natural sciences. Since Rasch focuses on the items and the persons rather than the test score, the synthesis of quantitative analysis with qualitative issues is experienced in a way that is rare in social science. Ultimately, Rasch measurement can facilitate more efficient, reliable, and valid assessment while improving privacy and convenience to users. The Workshop is useful for anyone who wants to understand the role of modern measurement in research.
Attendees will learn hands-on:
* Differences between Classical Test Theory and Rasch
* Why and how Rasch creates linear, interval measures
* The inner workings of the Rasch model
* How to run Winsteps analyses
* Interpretation of Rasch/Winsteps output
You need a recent Winsteps running on a lap-top computer. We provide Winsteps free, but time-limited.
For more details and registration: www.winsteps.com/workshop.htm
Rasch-related Coming Events: 2007
Feb. 12-16, 2007, Mon.-Fri. Item Response Modeling With ConQuest (Ray Adams & Margaret Wu), Australia www.edfac.unimelb.edu.au
Feb. 16 - Mar. 16, 2007, Fri.-Fri. Practical Rasch Measurement (Winsteps) online course (Mike Linacre) www.statistics.com/courses/rasch (Sorry! Fully booked.)
March 2007 - Dec 2008 3-day Rasch courses, Leeds, UK http://home.btconnect.com/Psylab_at_Leeds/
March 26-27, 2007, Mon.-Tues. Introduction to IRT/Rasch Measurement Using Winsteps (Conrad & Bezruczko), Chicago www.winsteps.com/workshop.htm
March 26-29, 2007, Mon.-Thurs. MetaMetrics Workshop Series in Psychometrics – Introduction to Rasch Measurement: Theory and Application (David Andrich) (free!), Durham, North Carolina www.lexile.com
Apr. 7-8, 2007, Sat.-Sun. Introduction to Rasch Measurement: Theory and Applications, Chicago IL (Smith & Smith) www.jampress.org
Apr. 9-13, 2007, Mon.-Fri. AERA Annual Meeting, Chicago www.aera.net
May 4 - June 1, 2007, Fri.-Fri. Facets online course
(Mike Linacre) www.statistics.com/courses/facets
June 21 - July 1, 2007, Thur.-Sun. 3rd Summer School Measurement of Latent Variables (Rasch), Russia
June 22, 2007, Fri. Workshop: Theory and Practice of Measurement of Latent Variables, Russia www.rasch.org/russia.pdf
July 16, 2007, Mon. ConQuest Workshop
(Margaret Wu), Taiwan
July 16, 2007, Mon. Winsteps Workshop
(Mike Linacre), Taiwan
July 17-19, 2007, Tues.-Thurs.
Pacific Rim Measurement Symposium PROMS
Taiwan
http://210.60.0.152/PROMS2007TAIWAN/
Aug. 3 - Aug. 31, 2007, Fri.-Fri. Practical Rasch Measurement with Winsteps online course (Mike Linacre)
www.statistics.com/courses/rasch
Rasch Online Courses
Winsteps and Facets
by Mike Linacre
May 4 - June 1, 2007, Fri.-Fri. Facets online course
(Mike Linacre) www.statistics.com/courses/rasch
Aug. 3 - Aug. 31, 2007, Fri.-Fri. Practical Rasch Measurement with Winsteps online course
(Mike Linacre) www.statistics.com/courses/facets
Feb. 16 - Mar. 16, 2007, Fri.-Fri. Practical Rasch Measurement with Winsteps online course (Mike Linacre) www.statistics.com/courses/rasch (Sorry! Fully booked.)
Each Course consists of 4 weeks of detailed step-by-step downloadable tutorials on Rasch theory and software operation. There are Discussion Boards for Q-&-A and group interaction. Free time-limited versions of the software are provided. These Courses are the next-best-thing to in-person Workshops. You work at your own pace in your own location on your own schedule. Give yourself at least 10 hours per week to fully benefit.
Rasch-related Coming Events: 2008
Jan. 7-11, 2008, Mon.-Fri. Introductory course on Rasch measurement (Andrich, RUMM), Australia www.rasch.org/i2008.htm
Jan. 14-18, 2008, Mon.-Fri. Advanced course on Rasch measurement (Andrich, RUMM), Australia www.rasch.org/i2008.htm
Jan. 21, 2008, Mon. One-day RUMM Workshop (Andrich, RUMM), Australia www.rasch.org/i2008.htm
Jan. 22-24, 2008, Tues.-Thurs. 3rd International Conference on Measurement in Health, Education, Psychology and Marketing: Developments with Rasch models, Australia www.rasch.org/i2008.htm
March 24-28, 2008, Mon.-Fri. AERA Annual Meeting
New York www.aera.net
Rasch Workshop
An Introduction to Rasch Measurement:
Theory and Applications
by Everett V. Smith Jr. & Richard M. Smith
April 7-8, 2007 - Saturday-Sunday
immediately before AERA
University of Illinois - Chicago
This training session on the theory and applications of Rasch measurement will provide participants with the necessary tools to become effective consumers of research employing Rasch measurement and the skills necessary to solve practical measurement problems. Instructional material will be based on four Rasch measurement models: dichotomous, rating scale, partial credit, and many-facet data. Participants will have the opportunity to use current Rasch software.
The format will consist of eight units:
˙ Introduction to Rasch Measurement
˙ Item and Person Calibration
˙ Dichotomous and Polytomous Data
˙ Performance and Judged Data
˙ Applications of Rasch Measurement I and II
˙ Examples of Rasch Analyses
˙ Analysis of Participants’ Data.
The material covered is these units is an overview of material that would normally be covered in approximately three graduate level measurement courses. Registration includes the full 2-day workshop, a continental breakfast each morning, over 550 pages of handouts and tutorial material, a copy of Introduction to Rasch Measurement (a 698 page book) and a one-year subscription to the Journal of Applied Measurement.
For more details and registration: www.jampress.org under Rasch Measurement Workshops
RMT 20:3 Miscellaneous Material, … Rasch Measurement Transactions, 2006, 20:3
The URL of this page is www.rasch.org/rmt/rmt203h.htm
Website: www.rasch.org/rmt/contents.htm