Research Carried out by LSAC and Some LSAT Statistics
Following is a list of a few research reports by the LSAC (Law School Admission Council):
- Admissions Policy Research Project: 2002-2003 by the Faculty of Law, University of Alberta
- An Analysis of Differential Validity and Differential Prediction for Black, Mexican American, Hispanic, and White Law School Students (RR 90-03 )by Linda F. Wightman and David G. Muller
- A Classical Test Theory Perspective on LSAT Local Item Dependence (SR 96-01) by Lynda M. Reese
- Factors in Performance on the Law School Admission Test (SR 93-04) by Kenneth M. Wilson and Donald E. Powers
- The Effect of COMC on the Stability of LSAT Item Parameter Estimates (SR 93-01) by Lynda Reese and Robert McKinley
Based on these reports a few examination statistics are derived and they reflect some aspects of the test. The official website of the test is: www.lsac.org and these reports and statistics are found in the research category of this website. There are almost 20-30 such reports in the website but let us analyze a few of these reports and understand a few statistics:
1. Assessing the Effect of Multidimensionality on LSAT Equating for Subgroups of Test Takers (SR 95-01) by Andre F. De Champlain- In simple terms, this study is to understand the relationship between the ethnicity and the test scores of the candidates. Certain researchers say that ethnicity affects the scores and the statistical averages which are derived to convey the scores are not the true reflections of the abilities of a candidate. The average scores are calculated based on scores of different question sets. This is why the test system of relative scores claims to negate the effects of the difference in the question sets answered by different students. According to this system, the total marks of each student taking the test are plotted on a graph and the score through that comparative graph is the score of the candidate. The range of the graph is between 121 and 180 where 120 is the lowest score and 180 the highest. Some assessment statistics claim to prove that students from certain races have historically performed better than other in every test. More than 16 statistical tables in this research finally conclude the negative correlation between scores and ethnicity. The fact still remains that every student should be measured based on all the academic data available on him/her along with the current scores. This research is very exhaustive but is not free of controversies because many researchers have tried to prove otherwise. The link for this research is http://www.lsac.org/LsacResources/Research/RR/RR-90-03.pdf
2. Factors in Performance on the Law School Admission Test (SR 93-04) by Kenneth M. Wilson and Donald E. Powers- LSAT is in many ways like the GRE (Graduate Record Examination). Both these checks measure skills through the multiple choice questions asked in the three different sections of the tests. This research paper tries to derive test statistics that prove that the questions asked in the tests are indeed capable of measuring the skill-sets of the candidates. The key tenets of this research paper are as follows:
- The study used different sample test papers and analyzed them.
- They then compared the samples against the GRE samples of the test takers.
- The research then proves that the questions are really able to match the questions to the skills required for law school admissions and thus the questions in the test are capable of skill measurement.
- Test statistics from more than 6 statistical tables prove that under the given test conditions, the abilities of a student are correlated to his or her scores and thus proving that, this is a test that can measure the skills of a candidate.
- The study is psychometric in nature and the analysis is very in-depth and thorough.
- This research is just a thesis to prove that the scores are not faulty, they truly reflect the admissibility of a candidate to law schools and that admissions to law schools consider holistic data of the candidates.
The link for this research is as follows: http://www.lsac.org/LsacResources/Research/SR/stat-reports.asp The LSAC website's research section is full of statistics and every candidate should take out time, before or after taking the exam, to try and go through these statistics so that they are well aware of all the nuances and discussions associated with the test.