A study of the context effects on item parameters for one- and three-parameter latent trait models showed that: (1) changes in context affected their item difficulties; and (2) context effects were more important in making predictions for single items than for groups of items. (Author/RL)

Responses of an unbiased random sample of students were compared with the responses of a self-selected sample for the evaluations of two medical school courses. When responses were investigated across items, the patterns of differences between the random and voluntary samples appeared to be unique to each class. (Author/MLW)

A device designed for sampling algae in rivers and streams is described. Techniques for observing algae in the laboratory as well as tips for maximizing success in sampling are given. (SA)

It is shown that using formulae for the estimation of sampling errors based on simple random sampling, when a design actually involves cluster sampling, can lead to serious underestimation of error. Jackknife and balanced repeated replication are recommended as techniques for dealing with this problem. (Author/CTM)

Details the procedures followed in obtaining a frequency-of-use list of the most-to-least-used instructional materials in mathematics (K-12), reading (K-6), and science and social studies (each 7-12). (Author/MLF)

Explores the relationship between pupil attainments on British National Curriculum Tests at the end of Key Stage 2, teacher assessments, and several pupil characteristics, such as gender and age) using representative samples drawn from schools in England from 1996-1998. Finds levels of agreement between teacher assessments and test results…

Studied the improvement in precision of population estimates from the inclusion of extensive covariates in the multivariate procedure that imputes values for the missing proficiencies. Analysis of data from the National Assessment of Educational Progress (samples of 10,291 eighth graders and 8,416 fourth graders) shows that improvement in…

The representativeness of behavioral observation samples with durations of less than the whole time of interest was investigated with five profoundly mentally retarded physically handicapped adults in an institutional setting. It was found that the session representativeness was a function of the relative duration of the behavioral categories and…

Arguing that reliable and valid dropout rate estimates are prerequisite to establishment of causal factors and intervention programs, this article examines differences in definitions of dropouts, computational methods, and the complexities in defining cohorts, as well as the importance of sample attrition. Several sources of error are discussed.…

The effects of certain characteristics (e.g., sample design) of National Assessment of Educational Progress (NAEP) data on statistical analysis techniques are considered. Ignoring special features of NAEP data and proceeding with a standard analysis can produce inferences that underestimate the true variability and overestimate the true degrees of…

Describes the teacher-developed California Assessment Program (CAP) writing measure, designed to support California's reform curriculum and based on matrix sampling techniques. This program will be supplemented by literature and mathematics assessments. The greatest challenge is designing an assessment to match the state's new history and social…

Reviews time-saving approaches that can help academic librarians (or small libraries lacking collection development librarians) to maintain collections. A sidebar provides information on locating subject publication lists and appendices offer guidelines for collection weeding and sampling. (JMV)

Several issues related to the design and reporting of results from the National Assessment of Educational Progress (NAEP) are discussed in the context of current expectations for the NAEP and its origins. These issues include: (1) content coverage and format; (2) estimation procedures; and (3) reporting problems. (SLD)

A test theory using only ordinal assumptions is presented, based on the idea that the test items are a sample from a universe of items. The sum across items of the ordinal relations for a pair of persons on the universe items is analogous to a true score. (SLD)

Describes the of attribute sampling to estimate characteristics of library collections and operations. The nature of statistical sampling and making a statistical inference are covered, and examples from library situations are given. Tables of determination of sample size and evaluation of results are included. (Contains six references.) (EAM)