An Investigation of Possible Causes for the Inadequacy of IRT Pre-Equating IRT SAT
- Author(s):
- Eignor, Daniel R.; Stocking, Martha L.
- Publication Year:
- 1986
- Report Number:
- RR-86-14
- Source:
- ETS Research Report
- Document Type:
- Report
- Page Count:
- 50
- Subject/Key Words:
- Equated Scores, Item Response Theory (IRT), Mathematical Models, Psychometrics, Scholastic Aptitude Test (SAT), Test Theory
Abstract
A previous study of pre-equating the Scholastic Aptitude Test (SAT) using item response theory provided unacceptable equating results for SAT-mathematical data. The purpose of this study was to investigate two possible explanations for these unacceptable pre-equating results. Specifically, the calibration process, which made use of the three-parameter model and LOGIST, and the linking procedure used to place parameter estimates on the same scale were further investigated in a two-stage process to see if either was responsible for the poor IRT pre-equating results found for the SAT-mathematical data in the previous study. (50pp.)
Read More
- Request Copy (specify title and report number, if any)
- http://dx.doi.org/10.1002/j.2330-8516.1986.tb00169.x