BILOG-MG is an extension of BILOG that is designed for the efficient analysis of binary items, including multiple-choice or short-answer items scored right, wrong, omitted, or not-presented. BILOG-MG is capable of large-scale production applications with unlimited numbers of items or respondents. It can perform item analysis and scoring of any number of subtests or subscales in a single program run. All the program output may be directed to text files for purposes of selecting items or preparing reports of test scores.
BILOG-MG implements an extension of Item Response Theory (IRT) to multiple groups of respondents. It has many applications in test development and maintenance. Applications of multiple-group item response theory in education assessment and other large-scale testing programs include the following features.
- Nonequivalent groups equating for maintaining the comparability of scale scores as new forms of the test are developed.
- Vertical equating of test forms across school grades or age groups.
- Analysis of Differential Item Functioning (DIF) associated with demographic or other group differences.
- Detecting and correcting for item parameter trends over time (DRIFT).
- Calibrating and scoring tests in two-stage testing procedures designed to reduce total testing time.
- Estimating latent ability or proficiency distributions of students in schools, communities, or other aggregations.
In addition, BILOG-MG provides for variant items that are inserted in tests for purpose of estimating item statistics, but that are not included in the scores of the examinees.
A list of examples discussed in the BILOG-MG Guide is given below, along with extra examples and a zip file containing all examples and data.
Extra examples (zipped)
SSI, Inc. offers a technical support service via e-mail. This service is only available to registered end users of the SSI software products. Click here to view SSI’s policy and procedures for obtaining technical support.