Using one simulated and two real data sets, the effects of the systematic variation of the item-selection procedure and the stepsize method on the operating characteristics of computerized adaptive testing (CAT) for instruments with polychotomously scored rating scale items were studied. The six rating scale CAT procedures used performed well.…

A means of generating an interstate cost-of-living (COL) index from market basket data collected at the standard metropolitan statistical area (SMSA) level is described. Models developed for four regions explain differences in the COL among over 180 SMSAs. An adjusted average teacher salary for each state is also generated. (TJH)

Provides example of use of exploratory growth modeling to examine changes over time in functioning of 172 families who underwent treatment in Project Good Start prevention program. Addresses within-family and between-family research questions. Results highlight heterogeneity across families in direction and rate of family function change and its…

This paper provides a method for analyzing data consisting of event sequences and covariate observations associated with Markov chains. The objective is to use the covariate data to explain differences between individuals in the transition probability matrices characterizing their sequential data. (TJH)

Issues the author has explored in his work on the philosophy of statistics are reviewed. Indeterminacy, the place of empiricism, questions of causation and causality, and explorations of language have preceded the study of objectivity. The relationship between objectivity and multivariate statistics is examined. (SLD)

Discusses how applications from microbiology and sociology can be used to involve students. Presents a physical context for critical concepts in a first-semester calculus course. (Author/ASK)

Describes the New Mexico High School Supercomputing Challenge, a year-long project sponsored by New Mexico Technet, Los Alamos National Laboratory, and other statewide institutions that engages high school students, teachers, and professionals in complex scientific problem-solving that include written reports, mathematical models, and…

Investigates school spending in Norway, using a disaggregated demand model augmented to include political factors. Disaggregates county governments' high-school spending to identify sources of variation in student/teacher ratio, nonwage spending per student, and student enrollment. Political strength holds down (construction) costs and allows for…

Describes and evaluates a learning model for information filtering and selective dissemination of information which is an adaptation of the generalized probabilistic model of information retrieval. The model is based on the concept of uncertainty sampling that allows for relevance feedback both on relevant and nonrelevant documents. (Author/LRW)

Describes a simple demonstration of the flow of sand through an orifice at the bottom of a sandbox. Advocates the experiment's use with dimensional analysis for students in an introductory physics course. (WRM)

Details the construction and design of two kinds of sundials appropriate for school or home use. (Author/WRM)

Explains a model to analyze direct teaching cost per student at the class level in the final two years of secondary schooling in Victoria, Australia. The model provides predictions for class size and unit cost for each learning area for various enrollment levels. Cost predictions for foreign-language classes were twice that of English classes.…

Summarizes results of a longitudinal study fitting multilevel models to three waves of data on literacy progress for three cohorts of Australian elementary students. Provides estimates of prior achievement and social background influences on student progress and examines effects of grouping practices and other classroom variables. Attentiveness…

Presents a microeconomic analysis of the choice of university degree course (3 year or 4 year course) Spanish students make on finishing their secondary studies and applies the developed binomial logit model to survey data from 388 high school graduates. Findings show the importance of various factors in determining the likelihood of choosing the…

Estimates a model allowing researchers to determine how much achievement on a 10th-grade standardized test can be explained by observable schooling resources and unobservable school, teacher, and class effects. Although few observable variables are significant test-score determinants, unobservable effects seem important in explaining student…