The relationships between class of degree in psychology from one department and (a) interview ratings, (b) two adult intelligence tests, and (c) advanced-level examinations were examined in a sample of 145 students from four-year groups. (Editor)

Discusses ethical issues surrounding passive and active parental consent procedures when minors are to be asked sensitive research questions, exploring parental rights and the effect of active consent procedures on response rates and sample bias. Response rates are reported from two studies in which active consent procedures were implemented. (SLD)

Using the characteristic curve method for dichotomously scored test items, the sampling distributions of equating coefficients were examined. Simulations indicate that for the equating conditions studied, the sampling distributions of the equating coefficients appear to have acceptable characteristics, suggesting confidence in the values obtained…

Describes the role and function of the census and discusses census taking and decision making about "counting" from two perspectives: the Supreme Court decision in Wisconsin vs New York, and the Census Bureau's current plans for the year 2000. Concluding comments explore the lessons learned from the 1990 census and the effect on the 2000…

An Edgeworth approximation for accurate significance probabilities for the Wilcoxon two-sample test is substantially simplified. A method is developed that allows quick calculations of very accurate probabilities. Exact formulas are given for most of the remaining cases, and tables are presented comparing the new simplification to likely…

A Monte Carlo study involving 1,000 random samples from each of 64 different population matrices investigated bias in both canonical correlation and redundancy coefficients. Results indicate that the Wherry correction provides a reasonable solution to this problem and that canonical results are not as biased as has been believed. (TJH)

Two computer-intensive procedures are presented for dealing with non-random selection in the development of samples for experimental, quasi-experimental, and survey designs associated with educational research. The procedures are randomization tests to clarify treatment effects and bootstrap techniques to estimate the uncertainty of…

Argues that the difficulties of identifying and estimating the size of any pools of citable items are so great that comparisons of citation counts are rarely valid, and that the relationship between the value of a work and its citation can only be assessed by careful study of the citing paper. (four references) (CLB)

Connecticut has two statewide student assessment programs. The Connecticut Assessment of Educational Progress uses sampling procedures to examine state program effectiveness periodically in 11 mandated subject areas. The Connecticut Mastery Tests annually monitor mathematics and language arts progress for every fourth-, sixth-, and eighth- grade…

Describes a school project to choose a mascot in which students learned about sampling and polls while collecting, organizing, and analyzing data. (MKR)

The use of cluster analysis, a multivariate classification technique, is advocated as a framework to guide the purposive selection of projects for multiple-case study research. A cluster analysis of a contrived data set demonstrates how the procedure is performed, and advantages and limitations are discussed. (SLD)

Suggest practical procedure for estimating number of subjects that need to be screened to obtain sample of fixed size that meets multiple correlated criteria. Procedure described is based on fact that least-squares regression provides good quadratic fit for Monte Carlo estimates of multivariate probabilities when they are plotted as function of…

This poem, with stanzas in limerick form, refers humorously to the many threats to validity posed by problems in research design, including problems of sample selection, data collection, and data analysis. (SLD)

Analyzed response bias among 34 recipients of care in hospice. Found nonrespondents to have better bereavement prognoses and tended to care for patients who were younger, male, and in program for shorter time. Nonrespondents were in contact with staff less than were respondents. Data are consistent with earlier research showing significant…

An approximate statistical test is derived for the hypothesis that the intraclass reliability coefficients associated with two measurement procedures are equal. Control of Type 1 error is investigated by comparing empirical sampling distributions of the test statistic with its derived theoretical distribution. A numerical illustration is…