The utility of the three-form design coupled with maximum likelihood methods for estimation of missing values was evaluated. Simulation studies demonstrate that maximum likelihood estimation and multiple imputation methods produce the most efficient and least biased estimates of variances and covariances for normally distributed and slightly…

Describes the history of the random experiment in the Home Office in the United Kingdom and demonstrates that research and the conduct of research is not an altogether rational process and that fashion, personality, and politics play a role in research policy and methodology choice. (SLD)

This article reviewed 55 studies to examine trends in interventions to improve the academic functioning of students with emotional disturbance. Results of descriptive analysis indicated: lack of demographic information; settings usually special education classrooms; predominantly single-subject designs; lack of treatment fidelity data; lack of…

Views intercoder reliability as a sampling problem for content analyses. Develops a formula for generating sample sizes needed to have valid reliability estimates. Suggests steps for reporting reliability. (TB)

Presents guidelines for supervising an undergraduate student doing research, including a sample contract set up between the student and the supervisor. The contract may state the research topic, objective, procedures, laboratory requirements, costs, schedule, additional projects, and grading criteria. Other suggestions include scheduled meetings…

This model for teaching quantitative research depicts five processes: build knowledge, formulate hypotheses, develop measures, pick analytical technique, and plan data collection. Exercises designed to integrate these elements are described: diagraming hypotheses, mapping measures onto constructs, matching analysis to hypotheses, matching analysis…

Discussion of the use of surveys as a research tool focuses on the value of library surveys. Two types of surveys are described, the descriptive survey and survey research; and improving the quality of survey research is discussed, including planning, sample size, data collection techniques, and methods of statistical analysis. (18 references)…

A methodology for determining the optimal number of observations to use in a measurement design when resource constraints are imposed is presented. Two- and three-facet designs are outlined. Parallel closed form formulae can easily be determined for other designs. (TJH)

Addresses the problem of research formulation for the inexperienced. Provides a model for geographic research, and identifies types of research problems. Discusses problem definition utilizing both the inductive and deductive method; literature searches; the data base; and methodology. Explores the role of theory, the theorizing process, and…

Long's article "Inside the Black Box" postulated that what happens inside the classroom is the most important factor in student performance. Here, Long's findings are reexamined, the benefits of more naturalistic inquiry are discussed, and a balanced qualitative and quantitative approach toward classroom foreign language learning research is…

This paper describes the parallel treatments design, a nested single subject experimental design that combines two concurrently implemented multiple probe designs, allows control for effects of extraneous variables through counterbalancing, and replicates its effects across behaviors. Procedural guidelines for the design's use and issues related…

The author replies to responses to her article, "The Newtonian Mechanistic Paradigm, Special Education, and Contours of Alternatives" (EC 220 916). Topics covered include the degree of objectivity versus the idea of objectivity, theory-data separation versus theory-laden data, Piagetian theory and the question of theory versus paradigm,…

Examines the roles of metaphysics in science and psychotherapy. Examines the views of Karl Popper and Imre Lakatos. Concludes that psychotherapy involves metaphysics in the following ways: (1) problem choice; (2) research and therapy design; (3) observation statements; (4) resolving the Duhemian problem; and (5) including anomalous results in…

Describes seven myths concerning reading-level-match designs, in which individual differences in reading acquisition are compared for groups of different ages matched on some aspect of reading performance. Gives examples from the reading literature to illustrate these myths and to suggest more realistic alternatives. Summarizes relevant…

Research articles published in 10 major journals during the years 1984-1987 were evaluated to determine how many satisfied the recommendations of the Council for Learning Disabilities' Research Committee on reporting subject data. Only 4 of the 277 articles included acceptable information in 7 recommended areas of subject data. (Author/JDD)