The population discrepancy between unstandardized and standardized reliability of homogeneous multicomponent measuring instruments is examined. Within a latent variable modeling framework, it is shown that the standardized reliability coefficient for unidimensional scales can be markedly higher than the corresponding unstandardized reliability…

Each year, policymakers, educators, and the general public engage in debates around the statewide average teacher pay figure that the North Carolina Department of Public Instruction (DPI) publishes on its website and reports to the National Education Association. These debates take up the important consideration of whether or not teachers are…

Null hypothesis significance testing (NHST) has been the subject of debate for decades and alternative approaches to data analysis have been proposed. This article addresses this debate from the perspective of scientific inquiry and inference. Inference is an inverse problem and application of statistical methods cannot reveal whether effects…

Apprentice and trainee data are reported by the State and Territory Training Authorities to National Centre for Vocational Education Research (NCVER) on a quarterly basis, starting at the September quarter of 1994. The set of data submitted that quarter is referred to as Collection 1. The sets of data submitted in subsequent quarters are referred…

It is common in regression discontinuity analysis to control for high order (third, fourth, or higher) polynomials of the forcing variable. We argue that estimators for causal effects based on such methods can be misleading, and we recommend researchers do not use them, and instead use estimators based on local linear or quadratic polynomials or…

Shneidman (1973) derived an estimate of six survivors for every suicide that, in the ensuing years, has become an assumed fact underlying public health messaging campaigns in support of suicide prevention and postvention programs worldwide, in spite of it lacking either empirical testing or validation. This report offers a first test designed to…

Missing data are a common occurrence in survey-based research studies in education, and the way missing values are handled can significantly affect the results of analyses based on such data. Despite known problems with performance of some missing data handling methods, such as mean imputation, many researchers in education continue to use those…

In this chapter, the authors discuss the issue of research design in conducting inquiry on college impact and demonstrate the importance of longitudinal pretest-posttest designs in maximizing the internal validity of findings. They begin by discussing the strengths and weaknesses of different types of research design in the college impact…

Apprentice and trainee data are reported by the state and territory training authorities to the National Centre for Vocational Education and Training (NCVER) on a quarterly basis, starting at the September quarter of 1994. The set of data submitted that quarter is referred to as collection 1. The sets of data submitted in subsequent quarters are…

Data analysis is critical to educational planning. Determining the number of school leavers is crucial for a school board when planning for interventions and supports. In researching the number of early school leavers in the province of Prince Edward Island, the method in which the data were reported affected the rates. Two critical considerations…

The sexual abuse of children has received a tremendous amount of attention in recent years. Accordingly, both the criminal justice and mental health systems deal with child molesters. Since much of the public concerns revolve around the potential dangerousness of any given child molester, practitioners are frequently responsible for making…

To investigate mistakes in the reporting of diagnostic efficiency statistics, all studies of the diagnostic performance of self-report scales in two psychological journals published between 1980 and 1991 were reviewed. Of 26 relevant studies, 9 had an error in calculation of diagnostic efficiency. Implications are discussed. (SLD)

Deliberations about social policy often center on estimates of harm or benefit generated by different interest groups. Problems in what is measured and how it is measured are illustrated by a discussion of research into sexual abuse and rape. Advocacy research is an unreliable foundation for social policy formation. (SLD)