ERIC Number: ED469245
Record Type: Non-Journal
Publication Date: 1995-May
Reference Count: N/A
Assessing the Effect of Multidimensionality on LSAT Equating for Subgroups of Test Takers. Statistical Report. LSAC Research Report Series.
De Champlain, Andre F.
This study investigated whether differences in the dimensional structure of the form of the Law School Admission Test (LSAT) across selected ethnic subgroups of test takers had any impact on equating results using an item response theory (IRT) true-score procedure. Whether there were any differences in the underlying latent trait composite across ethnic subpopulations that might yield noticeably different conversions for certain groups of test takers was studied. Data were from Caucasian (n=34,726), African American (n=3,548), and Hispanic (n=1,351) test takers. Results obtained with respect to the dimensionality of the LSAT with the three ethnic groups show that a two-dimensional model, specifying Analytical Reasoning and Logical Reasoning plus Reading Comprehension as the two factors, adequately accounted for the item responses of Caucasian and African American test takers, while a more complex model was required for the Hispanic subgroup. Equating results indicate that the differences between the conversion lines for the three ethnic groups and the total test-taker population were negligible. Results suggest that the African American and Hispanic conversion lines are statistically equivalent to the equating function for the majority Caucasian group and to one derived for the total test taker population. (Contains 5 tables, 15 figures, and 75 references.) (SLD)
Publication Type: Numerical/Quantitative Data; Reports - Research
Education Level: N/A
Authoring Institution: Law School Admission Council, Newtown, PA.
Identifiers - Assessments and Surveys: Law School Admission Test