This is the decade of data analytics and big data, but not everyone agrees with the definition of big data. Some researchers see it as the future of data analysis, while others consider it as hype and foresee its demise in the near future. No matter how it is defined, big data for the time being is having its glory moment. The most important…

Background/Context: Principles of evidential reasoning have often been discussed in the context of educational and psychological measurement with respect to construct validity and validity arguments. More recently, Mislevy proposed the metaphor of assessment as an evidentiary argument about students' learning and abilities given their…

In order to learn the concept of statistical techniques one needs to run real experiments that generate reliable data. In practice, the data from some well-defined process or system is very costly and time consuming. It is difficult to run real experiments during the teaching period in the university. To overcome these difficulties, statisticians…

There are two general methods of cross-validation: empirical estimation, and formula estimation. In choosing a specific cross-validation procedure, one should consider both costs (e.g., inefficient use of available data in estimating regression parameters) and benefits (e.g., accuracy in estimating population cross-validity). Empirical…

This paper describes DATASIM, a comprehensive software package which generates simulated data for actual or hypothetical research designs. DATASIM is primarily intended for use in statistics and research methods courses, where it is used to generate "individualized" datasets for students to analyze, and later to correct their answers.…

This report presents the results of a federally mandated study done to determine the best means of identifying, locating, and counting homeless children and youth, for the purpose of facilitating their successful participation in school and other educational activities. Several alternative approaches to obtaining consistent national estimates of…

Methodological challenges associated with structural equation modeling (SEM) and structured means modeling (SMM) in research on school violence and related topics in the social and behavioral sciences are examined. Problems associated with multiyear implementations of large-scale surveys are discussed. Complex sample designs, part of any…

At the request of the Office of the Assistant Secretary for Educational Research and Improvement, the Panel to Evaluate the National Center for Education Statistics (NCES) was established in 1985 by the National Academy of Sciences. This report culminates an extensive two-year study of NCES and reflects the panel's broad view of the center's…

Efforts to compare the costs of exactly the same things in different geographic regions involve comparisons of the same "market basket" of goods in two geographic areas. Measuring cost differences in education, however, is difficult, since most of the costs are in personnel, rather than in supplies. This publication explains the differences…

This is the third periodic report on the programs and plans of the National Center for Education Statistics (NCES). The challenge facing the NCES is to collect and analyze data that track the growth and change in educational experience in the United States. Current programs toward this goal, future plans, and major publications of the NCES are…