A MONTE CARLO STUDY OF ITEM SAMPLING (VERSUS TRADITIONAL SAMPLING) FOR NORM CONSTRUCTION1

Using a computer-based model of an item trace line, a random sampling experiment concerned with comparing item sample estimates to traditional (examinee) sample estimates of the mean and variance of a distribution of test scores was conducted. The results indicated that the optimal method for estimating a test's parameters may depend on several conditions. As expected, item sampling proved superior to traditional sampling in estimating test means under all conditions. However, with certain test lengths, ranges of item difficulty, and discrimination, traditional sampling provided better estimates of test variance than did item sampling.     

Science and the Ideals of Liberal Education

This article examines the influence of mathematics and science on theformation of culture. It then examines several definitions of liberaleducation, including the notion that languages and fields of study constitutethe substrate of articulate intelligence. Finally, it examines the linkagesbetween science, scientific culture, liberal education, and democracy, andproposes that science cannot be taught merely as a body of facts andtheories, but must be presented to students as integral with culturalstudies. The use of a contextualist approach to science education isrecommended.     

A META ANALYSIS OF THE VALIDITY OF PREDICTORS OF PERFORMANCE IN LAW SCHOOL

Although there is considerable evidence that the Law School Admission Test (LSAT) and the undergraduate grade-point average (UGPA) have a useful degree of predictive validity, there is also a large variation in the magnitude of the coefficients across schools. Understanding this variation has important implications for the use and interpretation of results of a validity study conducted at an individual school. A meta analysis of the validity results and data on applicants to 154 law schools was conducted in an effort to better understand this observed variation. The standard deviation (SD) on the LSAT and the correlation between the LSAT and UGPA for accepted students at each law school accounted for 58.5% of the between-school variance in the multiple correlations of these two predictors with first-year average grade in law school. Sampling error accounted for an additional 12% of the variance. Hence, only a small fraction of the between-school variability in validities remains to be explained by other statistical artifacts of situational specificity factors. Mean validities and 90% credibility values for four adjustment procedures are reported as are the mean observed validities for different combinations of predictors.     

Review of Ivey,Ivey, and Simek-Morgan's Counseling and Psychotherapy: A Multicultural Perspective

Counseling and Psychotherapy: A Multicultural Perspective (3rd ed.). Allen E. Ivey, Mary Bradford Ivey, & Lynn Simek-Morgan, with contributions by Harold E. Cheatham & Sandra A. Rigazio-DeGilio. Boston, MA: Allyn & Bacon, (1993), 374 pages ($50.00).     

ITEM BEHAVIOR ASSOCIATED WITH CHANGES IN THE NUMBER OF ALTERNATIVES IN MULTIPLE CHOICE ITEMS1

Language reading examinations in French and Spanish were administered to students in order to compare the behavior of “natural” four-choice items with “natural” five-choice items rescored as four-choice items after removing the least popular incorrect alternative. No significant differences in the regression systems of these items were found. However, “natural” four-choice items were significantly less reliable than “natural” five-choice items.