Machine learning methods for predictive analytics have great potential for uncovering trends in educational data. However, simple linear models still appear to be most widely used, in part, because of their interpretability. This study aims to address the issues of interpretability of complex machine learning classifiers by conducting feature…

The calls for accountability in higher education have made outcome-based assessment a key accreditation component. Accreditation remains a well-regarded seal of approval on college quality, and requires the programme to set clear, appropriate, and measurable goals and courses to attain them. Furthermore, programmes must demonstrate that…

In 1916 Robert Frost published his famous poem, "The Road Not Taken," in which he muses about what might have been had he chosen a different path, made a different choice. While counterfactual arguments in general can often lead to vacuous nowheres, frequently in statistics the data that are not presented actually exist, in a sense,…

The purpose of this study is to reveal school administrators' opinions on frequently changing regulations related to appointments and relocation and to offer a new model. A qualitative research design was employed. The study participants were 20 school principals and 20 vice principals working in the Ordu, Giresun and Trabzon city centres during…

Researchers use many different metrics for evaluation of performance of student models. The aim of this paper is to provide an overview of commonly used metrics, to discuss properties, advantages, and disadvantages of different metrics, to summarize current practice in educational data mining, and to provide guidance for evaluation of student…

In several subdomains of the social, behavioral, health, and human sciences, research questions are increasingly answered through mixed methods studies, combining qualitative and quantitative evidence and research elements. Accordingly, the importance of including those primary mixed methods research articles in systematic reviews grows. It is…

This article aims to reveal possibilities for teaching quality assessment when data from student survey are used. To achieve this aim, the conception of teaching in a higher education institution was reviewed and criteria of teaching quality were distinguished in the theoretical part. In the empirical part of the research, validity of teaching…

The Office of Planning, Research and Evaluation (OPRE), a unit within the Administration for Children and Families (ACF), is responsible for advising the Assistant Secretary for Children and Families on increasing the effectiveness and efficiency of programs to improve the economic and social well-being of children and families. In collaboration…

A study involving 11,804 British children (age 10) found that when specified criteria for dyslexia were used, 269 children qualified as dyslexic. These included 223 boys and 46 girls, for a ratio of 4.51 to 1. Difficulties in interpreting these data are discussed and a defense of the criteria is provided. (Author/CR)

A data-management system adhering to seven principles (concerned with defining and measuring characteristics and their interrelationships) is feasible and exists in parts, if not as an integrated whole. Present data-collection and reportage systems lack the real-time, analytic longitudinal characteristics that contemporary technology promises and…

The usefulness of state-by-state comparisons and other educational indicators is discussed in this paper, which seeks to improve report writing and data presentation skills. The first part offers an example of a policy report that uses key education indicators to describe the Arizona education system. Tables and data interpretation describe the…

Formative evaluation focuses on program modification based on ongoing measurement of student progress. The literature on formative evaluation for mildly handicapped students indicates that four measurement dimensions are critical: (1) focus of measurement; (2) frequency of measurement; (3) data display; and (4) data utilization methods. (Author/CB)

Data from nine Michigan elementary, middle, and high schools highlight the challenges and common strategies found in the use of student assessment data to meet public demands for accountability. The information gathered from assessment tools varies by frequency and type. Educators have, historically, underutilized data to guide practice because…

This guide is intended for local- and state-level vocational education administrators, planners, and evaluators who are responsible for making program planning and evaluation findings and decisions geared toward increasing program relevance. The method differs from more traditional approaches in its heavy reliance upon the selection and…