Many testing programs include a section of optional questions in addition to mandatory parts of a test. These optional parts of a test are not often truly parallel to one another, and groups of examinees selecting each optional test section are not equivalent to one another. This paper provides a general method based on missing-data methods for…

A correlational analysis was performed to examine the relationship between recognition and recall test formats. A total of 236 college students completed one of four 80-item general knowledge tests; the forms contained 20 items of each of four formats: (1) true; (2) false; (3) multiple-choice; and (4) free response. Ninety-three of the subjects…

To help determine the role that test instrument formats play in evaluation, two parallel examinations were given to 227 second-year medical students. The tests were based on information presented in a medical case history. One required students to generate their own problem lists (the generate group); the other required the students to select…

This study examined response bias in 108 female adolescents randomly assigned to one of three groups: (1) interactive computer interview; (2) face-to-face interview, or (3) self-administered questionnaire. Results showed no significant group differences on reports of sexual behavior, substance use or symptomatology. (Author/BS)

The effect on examinee performance of the rule that multiple-choice (MC) test items require the acceptance of 1 choice was examined for 106 dental students presented with choices in MC and multiple true-false formats. MC items force examinees to select one choice, which causes artificial acceptance of correct/incorrect choices. (SLD)

Describes study that investigated the effects of computerized test administration on undergraduates' responses to the Minnesota Multiphasic Personality Inventory (MMPI), and discusses methodological considerations important in evaluating the sensitivity of personality inventories in different administration formats. Results analyze the effects of…

Effects of numbers of experts (NOEs) and common items (CIs) on the scaling of cutting scores from expert judgments were studied for 11,917 physicians taking 2 forms of a medical specialty examination. Increasing NOEs and CIs reduced error; beyond 5 experts and 25 CIs, error differences were small. (SLD)

A developed computer-administered form of the Hamilton Anxiety Scale and the clinician form of the instrument were administered to 214 psychiatric outpatients and 78 community adults. Results support the reliability and validity of the computer-administered version as an alternative to the clinician-administered version. (SLD)

In his pioneer investigations of deductive logical reasoning competence, R. H. Ennis (R. H. Ennis and D. H. Paulus, 1965) used a multiple-choice format in which the premises are given, and it is asked whether the conclusion would then be true. In the adaptation of his work for use in Jamaica, the three possible answers were stated as…

Two of the most popular assessment instruments for measuring college student educational outcomes are the College Outcome Measures Program (COMP) of the American College Testing Program (1987) and the Academic Profile of the Educational Testing Service (ETS). Characteristics of these tests were compared, and the sensitivity of each test to…

The use of paper and pencil, videotape recordings, and microcomputers in student testing provide three very different views of student achievement. Paper and pencil tests can record how students compose tests and documents, and how they critique documents or performances. Video recordings can record how students explain ideas, answer questions,…

Three examinations administered to medical students were analyzed to determine differences among severities of judges' assessments and among grading periods. The examinations included essay, clinical, and oral forms of the tests. Twelve judges graded the three essays for 32 examinees during a 4-day grading session, which was divided into eight…

The random response technique was compared to a direct questionnaire, administered to college students, to investigate whether or not the responses predicted the social desirability of the item. Results suggest support for the hypothesis. A 33-item version of the Marlowe-Crowne Social Desirability Scale which was used is included. (GDC)

Reports that no significant difference in reliability appeared between a heterogeneous and a homogeneous form of the same general science matching-item test administered to 316 sixth-grade students but that scores on the heterogeneous form of the test were higher, independent of the examinee's sex or intelligence. (SB)

Studied 72 children for whom the following data were available: IQ score on a conventional test (WISC or Stanford-Binet); Goodenough-Harris drawing test IQ score; and behavior description by the test administrator. Personality traits of children who performed better on either the graphic or conventional IQ test were assessed. (SJL)