A model for the validation of standardized tests of academic achievement upon populations not represented in the samples used to standardize the tests is presented, and the results of a field testing of the model are described. The 1973 editions of the Stanford Achievement Test and the Test of Academic Skills were administered to a sample of…

The Arizona Tax Research Association analyzed the Arizona Teacher Proficiency Examination (ATPE). An item analysis of the 150 questions administered to 2,430 applicants from July 1982 through March 1983 was undertaken. A minimum point biserial correlation coefficient of .33 indicated the validity of an item. Nearly two-thirds (64 percent) of the…

Unidimensional item response theory (IRT) is widely used in the analysis and equating of educational achievement tests. If an IRT model is true, item response must be locally independent when the trait is held constant. Several measures of local dependence which are used in conjunction with the three-parameter logistic model in the analysis of…

Techniques for maximizing discrimination between groups in norm referenced measurement to reflect sensitivity to group differences inherent in the evaluation of multilevel educational systems are discussed. Data from the Beginning Teacher Evaluation Study (BTES) were used to examine relationships between reading and mathematics achievement and…

This report investigates an area of uncertainty in using the Angoff method for setting standards, namely whether or not a judge's conceptualizations of borderline group performance are realistic. Ratings are usually made with reference to the performance of this hypothetical group, therefore the Angoff method's success is dependent on this point.…

This report documents a computer program for simulation evaluation of item response theory (IRT) ability estimators. This Honeywell DPS version is a very slight modification of the program originally developed in FORTRAN-77 on a DEC VAX 11/780. The model of the world simulated by the program involves a unidimensional test in which the probability…

Two questions were investigated: (1) would rewording items on a questionnaire for evaluating faculty teaching effectiveness substantially affect students' ratings? and (2) would students' ratings of professors' teaching quality be totally consistent with their ratings of benefits derived from courses? (Author/RC)

The Responsiblity Test measures the secondary school student's level of knowledge (remembering or recall, understanding and thinking) of social responsibility, other types of responsibility, the benefits and costs of responsibility, the conditions and conflicts of responsibility, and ways of providing responsible behavior. It consists of 21…

It is usually assumed that the procedures followed in developing criterion-referenced (CR) educational achievement tests ensure their content validity. This assumption is reasonable for the class of "domain-specified" CR tests, in which the item domain is completely specified by item generation rules. However, most CR tests are of the…

Few phenomena in psychology have been studied more than reaction time. However, while response latency now provides the basic data for research in many areas of cognitive psychology, little work has been done on the problem of incorporating response latency in the measurement of individual differences. A solution to this problem requires the…

This study investigates whether item characteristic curves are the same for black students as for white students in the United States. The data analyzed were the answer sheets of 2269 black students and 2285 white students taking the 85-item Verbal Section of the College Board's Scholastic Aptitude Test. The study of item characteristic curves is…

One of a series of reports on the International Project for the Evaluation of Educational Achievement (in Mathematics).