THIS REPORT IS ONE OF A SERIES DESCRIBING NEW DEVELOPMENTS IN THE AREA OF RESEARCH METHODOLOGY. IT DEALS WITH LATIN SQUARES AS A CONTROL FOR PROGRESSIVE AND ADJACENCY EFFECTS IN EXPERIMENTAL DESIGNS. THE HISTORY OF LATIN SQUARES IS ALSO REVIEWED, AND SEVERAL ALGORITHMS FOR THE CONSTRUCTION OF LATIN AND GRECO-LATIN SQUARES ARE PROPOSED. THE REPORT…

In order to study procedures for increasing the return of mailed questionnaires, several types of cover letters were sent to groups of potential subjects. The three experimental variables were: (1) appeals to the potential respondent; (2) threat of a follow-up letter; and (3) stationery letterhead. Four types of appeals to the subject to…

This post-doctoral fellowship program, under the sponsorship of the Commission on Colleges, Southern Association of Colleges and Schools, was designed to provide a year of intensive study of the institutional self-study process and research design and methodology in higher education. The activities were divided into three overlapping phases and…

An inductive text to be used in introductory courses in educational research is presented. Rather than drawing conclusions for students, the author provides them with a series of exercises that allows them to experience what doing research actually means. The students learn to identify researchable issues, formulate and analyze research questions…

This article deals with methodological issues involved in conducting longitudinal research on the effects of aging. (JMB)

Some sampling characteristics of three estimators of the intraclass correlation were investigated under a variety of conditions within the context of a one-way analysis of variance. The results promote caution in the use of all three estimators. The three estimators differed very little in their bias or in their standard errors. (Author/JKS)

Procedures to estimate the magnitude of a treatment effect are examined for analysis of variance (ANOVA) designs which have repeated-measures. In particular, it is argued that the estimate of utility (strength of effect) for a within-subjects variable should be adjusted to reflect the underlying ANOVA model. (Author/JKS)

A FORTRAN computer program was derived for an IBM series 360/370 computer system that provides a factor analytic solution for large three-dimensional data matrices. The computational procedures employed are based upon those presented in Method III by Tucker. (Author/JKS)

Commentary is presented on the preceding articles in this issue of the journal. Critical commentary is made article by article, and some general recommendations are made. (See TM 503 664 through 670). (JKS)

Issues raised at an interdisciplinary conference on "Dialectics: a paradigm for the social sciences" are reviewed. The conference focused on the role of dialectical theory and methodology in designing and interpreting research in the social sciences. (BD)

Subroutines to calculate exact chi square and Fisher's exact probability tests are presented for 3 by 2 cross-classification tables. A nondirectional probability value for each test is computed recursively. (Author/GDC)

Discusses current themes in communication research. Claims that this research offers an increasingly sophisticated view of journalism as a reflection not of an objective reality, but of political-economic power and sociocultural conflict. Includes an example of an imaginary symposium and a strategy for reframing the journalistic quest for truth.…

Contends that theoretical and conceptual problems relating to the validation of assessment centers must be resolved before quantitative validation methods may be used. An open design is suggested to facilitate conceptual clarification. (CH)

Argues for the application of behavioral methods including natural observations over reification in parapsychological research. Research methodology stressing the importance of observation, replication, and continuity in applied science is discussed. (Author/BL)

Outlines costs and benefits associated with different cross-validation strategies; in particular the way in which the study design affects the cost and benefits of different types of cross-validation. Suggests that the choice between empirical estimation methods and formula estimates involves a trade-off between accuracy and simplicity. (JAC)