Search

Comparison data on SAT verbal and mathematical were collected on pairs of examinees in three samples for later use in detecting instances of willful copying. Two of the samples were constructed with the knowledge that no examinee could possibly have copied from the answer sheet of any other examinee in the sample. The third sample was taken entirely from a single center believed to be free of cheating. In each sample the answer sheet of each examinee was compared with the answer sheet of every other examinee. Eight detection indices were developed and distributions were run for possible operational use in making future judgments regarding examinees who were actually suspected of copying. Covariance analyses between samples indicated statistical but not practical significance, and consequently it was judged that any one of the samples could serve the purposes of operational detection as well as either of the other two. Empirical tryout of the indices against known and admitted copiers gave some results which permitted the elimination of three of the indices from further use. Practical considerations removed a fourth, and further statistical study eliminated two others. The remaining two have been in successful operational use at Educational Testing Service for more than two years. (Author)

A technique for detecting and studying item (or test) x group interactions independent of differences in level or dispersion of the groups is described. It involves construction of a scatter plot with two groups represented, one on each axis. Each point in the scatter plot represents the coordinates of a measure of a characteristic for one group plotted against a measure of the same characteristic for the other group; and the set of N points in the scatter plot represented the variables under study. The shape of the ellipse represents the degree to which the two groups in question share similar profiles. One method of analysis is to measure the departure of each point from the major axis of the ellipse and to study specific items that are most aberrant. Another is to calculate the variance associated with the item x interaction. Although the technique is not intended as a measure of item or test bias, it is useful in diagnosing cultural differences and comparing different types of groups. (Author/DJ)

This study examines a common set of equating items for their appropriateness to both American and Canadian populations and, to determine the equations for converting scores from the verbal and mathematical scales of the 1971 form of the Canadian Scholastic Aptitude Test (the future standard continuing scales of the CSAT) to the corresponding standard continuing scales of the Scholastic Aptitude Test. (AG)

Two-factor analyses of variance with multiple measurements on one factor were conducted for the five sections of the Test of English as a Foreign Language (TOEFL) and six language groups, and also for the items of each section, based on data collected at the first administration of this form of the test, in October 1969. the principal findings, that the Test x Group interaction and the Item x Group interactions were significant, indicated that some tests and some items were relatively more difficult for some language groups than for others. Displays of the Item x Group interactions were made by analyzing the item difficulty plots for each language group against a spaced sample of all candidates taking this form of the test in October 1969. A measure of the deviation of each item from the central tendency of the plot was developed, expressing the degree to which the item was especially difficult--or-easy--for a particular language group relative to the other items. Distributions of these measures are given for each of the five parts of TOEFL, for each of the six language groups. (Author)

Several samples of Black and White students were drawn from the 1970 PSAT administration in Georgia and studied for item x race interaction on both the verbal and mathematical sections of the test. When subsamples of candidates were drawn from their respective racial groups, matched on mathematical for the study of verbal items and matched on verbal for the study of mathematical items, there was an observable decrease in the size of the item x race interaction, suggesting that one factor contributing to that interaction was simply the difference in performance levels on the test shown by the two races. Further analyses demonstrated a moderate item x group interaction for Blacks native to different cities and a moderate item x group interaction for Blacks native to areas of different population density. (Author)

This report was prepared for the specialist who, well acquainted with the concepts and statistics of educational measurement, needs technical information about the Admissions Testing Program of the College Entrance Examination Board. It brings together the findings of a considerable number of studies of the Scholastic Aptitude Test (SAT) and the Achievement Tests. Three publications predated this book and they serve as a compendium of available information on the College Board Admissions Testing Program up to 1957 stressing proper test use and test interpretation for admissions and guidance. Recent manuals tend to be more interpretive than explicative. It is the aim of this book, however, to fill the information gap by providing the data needed for a comprehensive technical evaluation of the tests. In order to indicate the setting within which the program functions, a brief historical sketch, as well as administrative and psychometric considerations are briefly outlined. The scholastic Aptitude Tests and Achievement Tests are discussed and interpretive summary statistics for various subgroups of students are presented as are extensive validity studies of the admissions tests. Finally, the major findings of special studies that have been made in connection with the SAT and the Achievement Tests are summarized. (Author/CK)

The purpose of this study was to establish score equivalencies between the College Board Scholastic Aptitude Test (SAT) and its Spanish-language equivalent, the College Board Prueba de Aptitud Academica (PAA). The method of the study involved two phases: the selection of test items equally appropriate for Spanish- and English-speaking students for use in equating the two tests; and the equating analysis itself. The method of the first phase was to choose two sets of items, one originally appearing in Spanish, the other originally appearing in English; to translate each set into the other language; and to administer both sets in the appropriate language mode for pretest purposes to both types of students. These administrations were conducted in the Fall of 1970 with samples of condidates taking the PAA or the SAT at regularly scheduled administrations. They provided data regarding the difficulty and discrimination power of each item for each of the two groups, and an index of appropriateness of each item for both groups. On the basis of the analyses of these data, two sets of items, one verbal and the other mathematical, were chosen and assembled as "common items" to be used for equating. In the second phase of the study, these "common items," appearing in Spanish and in English, were administered in the appropriate language along with the operational form of the PAA in November 1971 and with the operational form of the SAT in January 1972. The data resulting from the administrations of these "common items" were used to calibrate for differences in the abilities of the two groups and permitted both linear and equipercentile equating of the two tests. Conversion tables are provided. (Author/DB)

Reviews norm-referenced and criterion-referenced testing. (SL)

The purpose of this study was to establish score equivalencies between the College Board Scholastic Aptitude Test (SAT) and its Spanish language equivalent, the College Board Prueba de Aptitud Academica (PAA). For the first phase, two sets of items, one originally appearing in Spanish and the other in English, were chosen; and each set was translated into the other language. Both sets were administered in the appropriate language mode for pretest purposes to samples of candidates taking the PAA or the SAT. They provided data regarding the difficulty and discrimination power of each item and an index of appropriateness of each item for both groups. On the basis of the analyses of these data, a set of items in Verbal and a set in Mathematical were assembled as "common items" to be used for equating. In the second phase, these common items, appearing in Spanish and English, were administered in the appropriate language with the operational form of the PAA and SAT. The data resulting from the administrations of these common items were used to calibrate for differences in the abilities of the two groups and permitted both linear and equipercentile equating of the two tests. Conversion tables relating the PAA-verbal to the SAT-verbal scores and the PAA-mathematical to the SAT-mathematical scores are given. Because of the scarcity of data at the upper end of the distribution of PAA scores, score equivalencies beyond the mid-700s were obtained by extrapolation. (Author/KM)

A two-factor analysis of variance with multiple measurements on one factor was conducted among the 40 items of the Vocabulary test of the Test of English as a Foreign Language (TOEFL) for six language groups. All sources of variance were found significant beyond the one per cent level. (Author/RC)