Lsac Research Report Series

The Law School Admission Council (LSAC) is a nonprofit corporation that provides unique, state-of-the-art products and services to ease the admission process for law schools and their applicants worldwide. Currently, 218 law schools in the United States, Canada, and Australia are members of the Council and benefit from LSAC's services. All law schools approved by the American Bar Association are LSAC members. Canadian law schools recognized by a provincial or territorial law society or government agency are also members. Accredited law schools outside of the United States and Canada are eligible for membership at the discretion of the LSAC Board of Trustees; Melbourne Law School, the University of Melbourne is the first LSAC-member law school outside of North America. Many nonmember schools also take advantage of LSAC's services. For all users, LSAC strives to provide the highest quality of products, services, and customer service. Founded in 1947, the Council is best known for administering the Law School Admission Test (LSAT ®), with about 100,000 tests administered annually at testing centers worldwide. LSAC also processes academic credentials for an average of 60,000 law school applicants annually, provides essential software and information for admission offices and applicants, conducts educational conferences for law school professionals and prelaw advisors, sponsors and publishes research, funds diversity and other outreach grant programs, and publishes LSAT preparation books and law school guides, among many other services. LSAC electronic applications account for 98 percent of all applications to ABA-approved law schools. Executive Summary When a test taker has prior knowledge about an administered test question (item), then this event is called item preknowledge, the test taker is called aberrant, and the item is called compromised. Item preknowledge negatively affects the corresponding testing program and its test score users (universities, companies, government organizations) because the scores produced for aberrant test takers will be invalid. The performance of eight statistics for detection of item preknowledge (five existing, two modified, and one new) was studied via computer simulations. Three major factors that could potentially influence the performance of the statistics were considered: (a) the type of test (adaptive, in which the next administered item is selected based on the test taker's responses to previously administered items; or nonadaptive, in which all test takers are administered the same group of items); (b) distribution of the aberrant population (normal or uniform); and (c) noise in the information about compromised items (since different groups …