Simplicity and efficiency in design and estimation are all important in deciding on sampling strategies. A simple model is given and illustrated for four practical situations to show how a good sampling strategy should be selected. (Author)

Reviews the research on sampling for daily newspapers and explores various sampling techniques for weekly newspapers. Contrasts different sample types to assess their utility in representing weekly newspaper content. Uses five content measures and tests three sampling techniques: simple random sampling and two "constructed year" samples,…

Raises concerns about unexamined conceptual assumptions and over-generalizations of research findings in the comparative management area. Suggests two ways of combating these problems: collaboration and accounting for complexities of culture. (SR)

Discusses common beliefs and flaws in classroom research. Distinguishes among three kinds of empirical educational investigations. Suggests research designs which are considered to be sensible, selective, sound, sensitive, and simple. Describes designs using multiple classrooms for instructional-intervention experiments. (KS)

Review of research methodologies used in studies of online public access catalog (OPAC) users finds that a variety of research methodologies--e.g., surveys, transaction log analysis, interviews--have been used with varying degrees of expertise. It is concluded that poor research methodology resulting from limited training and resources limits the…

Discusses two approaches to data analysis in pretest-posttest research designs in which researcher has not formed groups based on pretest or used pretest information in assigning participants to groups, thus ruling out two-way analysis of variance. Describes use of repeated-measures analysis of variance and two-group analysis of covariance in…

Argues that a definition of interactional argument based primarily on disagreement should be rejected in favor of a more traditional definition based on reason giving. Argues that views of ordinary arguers need not be given priority over those of experts. (SR)

Rejects Robert Rowland and J. Kevin Barge's conclusion (in an article in the same issue) that defining argument as reason giving is superior to defining argument as disagreement. Maintains that defining argument as disagreement is appropriate for an interpretive argumentation theorist, and that argumentation is a complex topic with room for more…

Addresses Pamela Benoit's response to an article in the same issue by the authors, restating key arguments of why a research focus on reason giving is superior to a research focus on disagreement. (SR)

A survey of studies in the "Journal of Speech and Hearing Disorders" and the "Journal of Speech and Hearing Research" found that only 12 direct replications and 15 systematic replications appeared in a total of 271 studies. Based on the probabilities of false findings in this literature, replication is recommended to verify…

Applied structural equation modeling to evaluation of cross-lagged panel models. Self-reports of physical and mental health at three time points spanning four-year interval were analyzed to illustrate cross-lagged analysis methodology. Data were analyzed from 856 patients with hypertension, diabetes, heart disease, or depression. Cross-lagged…

Assessed effects of three-week break on elementary students with and without mild disabilities in mathematics. Found that regression was not indicated when levels of comparison were examined, although levels of performance for students with and without disabilities differed significantly after break. Students with positive prebreak trends were…

Responds to Sarah J. McCarthey's article in the same issue. Considers particularly the limitations of McCarthey's research design. (HB)

Critiques Lytton's article in this issue that argues against focusing on the relative strength of child effects versus environmental effects. It is recommended that researchers should instead focus on the issues on which mechanisms operate and how they interact during transactional development. (RH)

Designed three-factor experiment to evaluate potential for improving first-session performance of six trainee-therapists as measured by postsession client ratings (n=48). Rather than through standardizing therapist behavior by using training manual beforehand, therapist effects were handled through statistical control. Found that more frequent…