There are times in survey research when missing values need to be estimated. The robustness of four variations of regression and substitution by mean methods was examined using a 3x3x4 factorial design. The regression variations included in the study were: (1) regression using a single best predictor; (2) two best predictors; (3) all available…

This study developed and investigated an empirical sampling distribution of the congruence coefficient. The effects of sample size, number of variables, and population value of the congruence coefficient on the sampling distribution of the congruence coefficient were examined. Sample data were generated on the basis of the common factor model and…

A new approach to assessing unexpected differential item performance (item bias or item fairness) is introduced and applied to the item responses of different subpopulations of Scholastic Aptitude Test (SAT) takers. The essential features of the standardization approach are described. The primary goal of the standardization approach is to control…

The effects of variations in degree of range restriction and different subgroup sample sizes on the validity of several item bias detection procedures based on Item Response Theory (IRT) were investigated in a simulation study. The degree of range restriction for each of two subpopulations was varied by cutting the specified subpopulation ability…

A Monte Carlo study was conducted to estimate the efficiency of and the relationship between five equations and the use of cross validation as methods for estimating shrinkage in multiple correlations. Two of the methods were intended to estimate shrinkage to population values and the other methods were intended to estimate shrinkage from sample…

This report presents considerations for sample design and estimation procedures for the Health Examination Survey, one of the major survey programs employed by the National Center for Health Statistics. The survey collects data which provide national estimates and distributions of various health characteristics related to the growth and…

This article argues that the 1981 work of Carbno presented unwarranted conclusions because its design included an improper operationalization of the object of measurement, given the problems addressed, and because the sample sizes employed were too small. (Author/PN)

Three numerical coefficients for analyzing the validity and reliability of ratings are described. Each coefficient is computed as the ratio of an obtained to a maximum sum of differences in ratings. The coefficients are also applicable to the item analysis, agreement analysis, and cluster or factor analysis of rating-scale data. (Author/BW)

This study addressed statistical techniques that might ameliorate some of the sampling problems currently facing states with small populations participating in State National Assessment of Educational Progress (NAEP) assessments. The study explored how the application of finite population correction factors to the between-school component of…

Job analysis has played a fundamental role in developing and validating licensure and certification examinations, but research on what constitutes reliable and valid job analysis data is lacking. This paper examines the reliability and validity of job analysis survey results. Generalizability theory and the multi-facet Rasch item response theory…

This technical report provides an updated assessment of the problem of optimizing the periodicity of the Schools and Staffing Survey (SASS). Making use of data from three rounds of SASS data collection (for school years 1987-88, 1990-91, and 1993-94), the report extends and updates the preliminary findings and interim assessments that were…

States participating in the National Assessment of Educational Progress State Assessment program (state NAEP) are required to sample at least 2,500 students from at least 100 schools per subject assessed. In this ideal situation, 25 students are assessed for a subject in each school selected for that subject. Two problems have arisen: some states…

In examining considerations in determining sample sizes for factor analyses, attention was given to the effects of outliers; the standard error of correlations, and their effect on factor structure; sample heterogeneity; and the misuse of rules of thumb for sample sizes. (Author)

A Monte Carlo approach was used to examine bias in the estimation of indirect effects and their associated standard errors. Results illustrate the adverse effects of nonnormality on the accuracy of significance tests in latent variable models estimated using normal theory maximum likelihood statistics. (SLD)

Describes item response and information functions for the Zinnes and Griggs paired comparison item response theory (IRT) model (1974) and presents procedures for estimating stimulus and person parameters. Monte Carlo simulations show that at least 400 ratings are required to obtain reasonably accurate estimates of the stimulus parameters and their…