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…

Discussion of sampling methods used in information science research focuses on Fussler's method for sampling catalog cards and on sampling by length. Highlights include simple random sampling, sampling with probability equal to size without replacement, sampling with replacement, and examples of estimating the number of books on shelves in certain…

Problems in selection of optimal designs in item-response theory (IRT) models are resolved through a sequential design procedure that is a modification of the D-optimality procedure proposed by Wynn (1970). This algorithm leads to consistent estimates, and the errors in selecting the abilities generally do not greatly affect optimality. (SLD)

A practical theory is offered for probing external validity, the generalization of causal relationships. This alternative theory is built around five principles abstracted from research on construct validation. It emphasizes purposive sampling for theoretical ends rather than random sampling to represent a population. (SLD)

Assesses the reliability of the National Longitudinal Survey of Youth (NLSY) data in terms of attrition patterns, characteristics of attriters and returners, and comparability with the Current Population Survey (CPS). Explores how attrition might corrupt the picture of labor-market experience and attempts to reconcile discrepancies between the CPS…

This study examined the representativeness of a time-sampling observational procedure to evaluate students with behavior disorders by examining error in samples of varying size in comparison to a criterion measure. Analyses of both single subject and multiple subject designs suggested that samples of 16 to 20 observational sessions of eight-minute…

Discussion of speech sampling in the assessment of children with phonological disorders focuses on the use of nonlinear phonological analysis, a method whereby multiple aspects or levels of a child's phonological system are examined. Principles and suggestions offer general guidance for adequate sample elicitation. (Contains references.)…

Limiting data collection to a sample group is one way to increase effectiveness in dealing with data. The paper describes how to draw a sample group (random sampling, stratified random sampling, purposeful sampling, and convenient or opportunity sampling) and discusses how to determine the size of the sample group. (SM)