From CRMDA
Contents |
Item Response Theory: Foundations of Test Development and Validation
Five-day Course • June 17 - 21, 2013• Lawrence, Kansas
Presented by the Quantitative Training Program of Psychology and the Center for Research Methods and Data Analysis at the University of Kansas.
Overview
Theoretical and practical advantages of scaling assessment data using IRT. Introduction to various IRT models and their applications, including software training and opportunities for students to analyze their own data.
Objectives
The purpose of this course is to acquaint students with the fundamentals of Item Response Theory (IRT). IRT is a latent variable approach to scaling assessments which offers many advantages compared to traditional approaches to scaling. To be successful research practitioners in IRT, two factors are important: (1) familiarity with various IRT models, and (2) the ability to interpret and apply these models appropriately. This course will therefore begin with presentation of popular models, their estimation, and proper interpretation, and then continue reinforcing these lessons throughout the week with examples and applications using educational and psychological test data. The goals of the class are to introduce the major models and assumptions, basics of parameter estimation, and useful applications which may be implemented, including conditional reliability analysis, test score linking and equating, evaluation of dimensionality and differential item functioning, and adaptive testing. We will balance our time between theoretical perspectives and practical applications, so learning to use software to estimate IRT models will be an important component of the class. Time will also be made to help students analyze their own data using IRT techniques.
Audience
The IRT summer course is geared to individuals who are interested in the foundations and applications of item response models as tools for measuring mental traits across disciplines. Information will be taught with a minimum of technical detail, catering to all skill levels. We welcome educational measurement professionals from testing companies, state educational assessment programs, and national testing programs, along with students, professors, and academic researchers. Participants from a variety of fields, including sociology, psychology, education, human development, business, and communication, will benefit from the course.
Instructors
William P. Skorupski, Ed.D., is an Associate Professor of Psychology and Research in Education at the University of Kansas. He earned his doctorate from the University of Massachusetts in 2004 and has been teaching psychometrics and conducting theoretical and applied research in IRT for over a decade.
Textbook
The Theory and Practice of Item Response Theory (de Ayala, 2009)
Software and Computer Support
Participants should bring a laptop computer. The course will utilize software developed for estimation of item response models from Scientific Software International. Participants should download the fully functional 15-day trial versions of BILOG-MG and PARSCALE for use during the course. These may be downloaded at the following URL: http://www.ssicentral.com/irt/downloads.html
We will also be making use of R for some of our applications. R is a very general software platform with great capability. It is open-source and completely free, and may be downloaded at the following URL: http://www.r-project.org/ (Click “download R” and follow instructions for choosing a download site {we have one at KU!} and preferred operating system).
Download these programs and get to know them as soon as possible. We will focus on theory before applications, but we’ll be using these programs before you know it.
Syllabus
Foundations of Test Development and Validation
William P. Skorupski
University of Kansas
| Monday | June 17, 2013 |
| 9:00 – 9:45 | Welcome and Introductions |
| 9:45 – 10:30 | Basic IRT Concepts, Models, and Assumptions |
| 10:45 – 12:00 | Basic IRT Concepts, Models, and Assumptions |
| 12:00 – 1:00 | Lunch * |
| 1:00 – 3:00 | Model Specifications and Scale Characteristics |
| 3:15 – 5:00 | IRT Models for Polytomous Response Data |
| 5:00 – 8:30 | Free BBQ (burgers, veggie burgers, brats) and open beer/wine bar at Holiday Inn |
| Tuesday | June 18, 2013 |
| 9:00 – 10:30 | Item and Trait/Ability Parameter Estimation |
| 10:45 – 12:00 | Item and Trait/Ability Parameter Estimation continued |
| 12:00 – 1:00 | Lunch * |
| 1:00 – 2:45 | Software: Introduction to BILOG-MG and PARSCALE |
| 3:00 – 5:00 | Individual consultations, Q&A |
| 5:45 | Free Bus to Downtown departs |
| 8:45 | Free Bus returns from Downtown |
| Wednesday | June 19, 2013 |
| 9:00 – 10:30 | Software continued, Evaluation of Model Fit |
| 10:45 – 12:00 | Test Reliability using IRT, Test Development |
| 12:00 – 1:00 | Lunch * |
| 1:00 – 3:00 | Test Score Linking and Equating |
| 3:15 – 5:00 | Individual consultations, Q&A |
| 5:45 | Free Bus to Downtown departs |
| 8:45 | Free Bus returns from Downtown |
| Thursday | June 20, 2013 |
| 9:00 – 10:30 | Test Score Equating Continued |
| 10:45 – 12:00 | Introduction to Item and Test Bias; Differential Item Functioning (DIF) |
| 12:00 – 1:00 | Lunch * |
| 1:00 – 3:00 | DIF continued |
| 3:15 – 5:00 | Individual consultations, Q&A |
| 5:45 | Free Bus to Downtown departs |
| 8:45 | Free Bus returns from Downtown |
| Friday | June 21, 2013 |
| 9:00 – 10:30 | Overview of Advanced IRT applications: CAT, Multidimensional, testlets, raters |
| 10:45 – 12:00 | Advanced IRT continued |
| 12:00 – 1:00 | Lunch * |
| 1:00 – 4:00 | Individual consultations, Q&A |
* Our group lunch is included in the Holiday Inn room rate and tickets for the group lunch are also available for purchase for those not staying at the Holiday Inn. There are other lunch options in Lawrence as well.
Course Files
Below are links to course files for those who enrolled in the course. The files are password protected to respect the intellectual property rights of the instructors. By using your login information you agree not to share your login information or the content protected by it.
Coming soon.
Contact Information
For information on course content, contact William P. Skorupski
A full list of prices and fellowship opportunities for this course and all the courses offered at this year's Summer Institutes in Statistics can be found on the Fees and Registration Page.