Realist evaluation (RE) is a research design increasingly used in program evaluation, that aims to explore and understand the influence of context and underlying mechanisms on intervention or program outcomes. Several methodological challenges, however, are associated with this approach. This article summarizes RE key principles and examines some…

Data Envelopment Analysis (DEA) is a widely adopted non-parametric technique for evaluating R&D performance. However, traditional DEA models often struggle to provide reliable solutions in the presence of data uncertainty. To address this limitation, this study develops a novel robust super-efficiency DEA approach to evaluate R&D…

Missing data are ubiquitous in studies examining preventive interventions. This missing data need to be handled appropriately for data analyses to yield unbiased results. After a brief discussion of missing data mechanisms, inappropriate missing data treatments and appropriate missing data treatments, we review the current state of missing data…

Many ethical concerns in online big data research stem from a pervasive assumption that data are disembodied and place-less. While some scholars have begun addressing the ethical dilemmas of big data, few offer approaches or tools that fully grapple with the situatedness of online data and its ethical implications. We draw on feminist new…

This report aims to showcase the value of implementing a Bayesian framework to analyse and report results from international large-scale surveys and provide guidance to users who want to analyse the data using this approach. The motivation for this report stems from the recognition that Bayesian statistical inference is fast becoming a popular…

Social network data often contain missing values because of the sensitive nature of the information collected and the dependency among the network actors. As a response, network imputation methods including simple ones constructed from network structural characteristics and more complicated model-based ones have been developed. Although past…

Categorical data become increasingly ubiquitous in the modern big data era. In this dissertation, we propose novel statistical learning and inference methods for large-scale categorical data, focusing on latent variable models and their applications to psychometrics. In psychometric assessments, the subjects' underlying aptitude often cannot be…

The aim of this paper is to introduce a software that is appropriate for the generalizability theory for not only balanced but also unbalanced data sets. Because it is possible to have unbalanced data sets while conducting a study, the researchers have devised an easy solution, other than deleting data, to balance the design to cope with this…

Education researchers are increasingly interested in applying data mining approaches, but to date, there has been no overarching exposition of their methodological advantages and disadvantages to the field. This is partly because the use of data mining in education research is relatively new, so its value and consequences are not yet well…

Randomised trials are often funded by commercial companies and methodological studies support a widely held suspicion that commercial funding may influence trial results and conclusions. However, these studies often have a risk of confounding and reporting bias. The risk of confounding is markedly reduced in meta-epidemiological studies that…

The present study explores how the visualization of an actor network enables researchers to understand mediating processes better by investigating relationships and effects among elements and entities other than human-actor accounts. In particular, the study presents how visualization may facilitate an understanding of the dynamics and structures…

Research synthesis is the practice of systematically distilling and integrating data from many studies in order to draw more reliable conclusions about a given research issue. When the first edition of "The Handbook of Research Synthesis and Meta-Analysis" was published in 1994, it quickly became the definitive reference for conducting…

Data sprints have emerged as a popular way to involve stakeholders in datawork. In this chapter we discuss what it takes to turn a sprint into a productive situation of inquiry (in the sense of Dewey, 1938). We argue that sprint organizers must work actively to counteract an otherwise docile setting where the preference for agreement between…

Connecting teachers' perspectives with their practice is an enduring challenge shaping what and how we understand teaching. Researchers tend to bifurcate teachers' work between their private and their public lives. These "worlds" bring particular meanings that are rendered through the analyses of visual documentations of teaching and…

The unstructured multiple-attempt (MA) item response data in virtual learning environments (VLEs) are often from student-selected assessment data sets, which include missing data, single-attempt responses, multiple-attempt responses, and unknown growth ability across attempts, leading to a complex and complicated scenario for using this kind of…