Comparison of earnings between control and experimental groups subsequent to participation in experimental training programs provides a credible estimate of program effectiveness. Too much of the nonexperimental estimation of the effects of training programs seems dependent on models that cannot be subjected to powerful statistical tests. (MLF)

A study of citations in instructional development (ID) periodical literature identifies invisible colleges--groups linked by common ideas or approaches--in the ID field. Although ID literature as a whole was weakly based on previous work, this study found eight invisible colleges and 10 authors who dominate the literature. (MBR)

Results of an investigation designed to determine whether the impact factor or the immediacy index--two derivative measures of citation analysis--provide useful insights into qualitative relationships among scientific journals indicate that neither measure is significant. (MBR)

This study describes the research articles published during 1980 in 41 core library journals and reports data for each source article: journal, research methodology, subject, total number of references, and number of references to journal articles. List of journals included in study and 12 tables are appended. (9 references) (EJS)

This study of catalog headings for corporate names entered in direct order which appeared in 1981 bibliographic records of the Library of Congress, National Library of Canada, British Library, and National Library of Australia reveals that an average of 87.2 percent of each agency's headings matched one or more of others. (EJS)

Examines relationships among the parameters of the Zipf size-frequency distribution as well as its sampling properties. Highlights include its importance in bibliometrics, tables for the sampling distribution of the maximal value of a finite Zipf distribution, and an approximation formula for confidence intervals. (Author/LRW)

Subjects in a study of analogic reasoning use in learning a computer language read text describing an invented LISP dialect and then solved problems and described language constructs. Five of six factors studied indicating use of analogy with a familiar computer language showed statistically significant results, supporting the hypothesis.…

This study explored the use of the monographic literature in British and American literary studies and compared its findings with those of studies of humanities journals. It was found that book references were the predominant tool for humanities scholarship and that manuscripts were cited almost as often as journal articles. (EJS)

Investigates interrelationships among five citation measures which indicate citation frequency and citation immediacy in scientific and technical journals (number of cited items, cited-citing ratio, impact factor, decay index, immediacy index) and impact of three factors on these measures (difference of fields, number of articles, number of citing…

Analyzes changing information values of journal article titles (measured by counting total number of words, number of keywords, and computing proportion of substantive words). Use of linear regression to determine change patterns for sample of titles from four selected journals, six library journals, and six miscellaneous journals (1951-1980) is…

The Generalized Inverse Gaussian-Poisson Distribution is suggested as an all-embracing mathematical model for bibliometric frequency distributions. Twelve examples are given which show that the new model cannot be rejected by virtue of an objective chi-squared test. A mathematical appendix and 20 references are included. (Author/EJS)

Describes a methodology for deriving educational expenditure estimates for handicapped children. Information collected for 573 children from three urban school systems from record reviews and interviews with the childrens' parents, teachers, and physicians reveals an approximate 2:1 ratio of expenditures for special and regular education students.…

Findings of study of book reviews selected randomly from six library journals (360 reviews for 1972-1974 publications; 360 reviews for 1978-1980 publications) reveals that for both time periods, core of 20-30 large trade publishers issued majority of books reviewed in journals and received higher number of multiple reviews. (Twenty-one references…

This paper provides researchers with a method of determining sample size for a given power level in the preparation of a single group exploratory repeated measure analysis. The rationale for determining sample size which takes into consideration the powers and assumptions of both the adjusted univariate and multivariate repeated measures tests is…

To test validity of cocitation studies as representations of intellectual structure, five-six years of aggregate cocitation data for 41 authors in macroeconomics and 49 authors in genetics of fruit flies were compared with independent judgments of interauthor similarity collected from 14 macroeconomists and 15 geneticists via a card-sorting…