It is widely believed that regression models for binary responses are problematic if we want to compare estimated coefficients from models for different groups or with different explanatory variables. This concern has two forms. The first arises if the binary model is treated as an estimate of a model for an unobserved continuous response and the…

As a research field geared toward understanding and improving learning, Learning Analytics (LA) must be able to provide empirical support for causal claims. However, as a highly applied field, tightly controlled randomized experiments are not always feasible nor desirable. Instead, researchers often rely on observational data, based on which they…

Standard models for network meta-analysis simultaneously estimate multiple relative treatment effects. In practice, after estimation, these multiple estimates usually pass through a formal or informal selection procedure, eg, when researchers draw conclusions about the effects of the best performing treatment in the network. In this paper, we…

One overarching question in scholarly methodological discussions on qualitative comparative approaches concerns how it is possible to compare and generalise deep insider knowledge across (nationally) specific contexts. The aim of this article is to propose a research strategy that both facilitates the comparison and theorisation of such knowledge…

Experimental studies are often employed to test the effectiveness of teaching innovations such as new pedagogy, curriculum, or learning resources. This article offers guidance on good practice in developing research designs, and in drawing conclusions from published reports. Random control trials potentially support the use of statistical…

Treatment effect estimates from a "regression discontinuity design" (RDD) have high internal validity. However, the arguments that support the design apply to a subpopulation that is narrower and usually different from the population of substantive interest in evaluation research. The disconnect between RDD population and the…

This paper presents best practices for conducting survey research using Amazon Mechanical Turk (MTurk). Readers will learn the benefits, limitations, and trade-offs of using MTurk as compared to other recruitment services, including SurveyMonkey and Qualtrics. A synthesis of survey design guidelines along with a sample survey are presented to help…

The use of "radar charts" is an increasingly popular way to present spatial data in a visually interesting format. Some authors recommend using "filled radar charts" to compare the performance of observational units. Filled radar charts are not appropriate for such comparisons because the size of the area within the polygon is not invariant to the…

Despite the value of the comparative perspective for the study of higher education is widely recognised, there is little consensus about the specific methodological approaches. Quantitative tools outlined their relevance for addressing comparative analyses since they are supposed to reducing the complexity, finding out and graduating similarities…

This article introduces the special issue, which focuses on the ways in which educational institutions in Europe and North America are responding to the growing number of children of immigrants entering schools and universities. It discusses the ways in which the needs of children of immigrants differ from those of native-born students, and the…

Formative and design experiments represent a methodology uniquely suited for educational research. Providing a practical overview of this emerging approach, the authors address the following questions: What is the origin of formative and design experiments and how do they compare to other approaches to investigating interventions in classrooms?…

The viability of the FORTRAN computer language and its relationship to other languages (such as PASCAL) were discussed. A library of C language and assembly language FORTRAN-callable subroutines, developed for the use of behavioral science researchers, was introduced. (Author/GDC)

This article describes four single-subject research designs comparing two or more interventions with young disabled children--the multitreatment design, alternating treatments design, adapted alternating treatments design, and parallel treatments design. Problems in using these designs include multitreatment interference, nonreversibility of some…

Criteria for suitable research designs for use with large databases are suggested and analyzed. The advantages and disadvantages of several types of quasi-experimental designs are compared. Examples are taken from the authors' research with data from the Manitoba Health Services Commission. (Author/AL)

Discusses operational terms used to denote Hispanic American populations; presents a typology for determining the comparability of studies of different Hispanic groups (through comparison of certain group characteristics); and demonstrates the application of the typology in comparing three research studies. (MJL)