Trend scoring constructed response items (i.e. rescoring Time A responses at Time B) gives rise to two-way data that follow a product multinomial distribution rather than the multinomial distribution that is usually assumed. Recent work has shown that the difference in sampling model can have profound negative effects on statistics usually used to…

In this paper I try to 'rethink' consistency as an educational quality for the 3rd millennium, following Italo Calvino's choice to take it up in his lecture series Memos for the Next Millennium, and despite the fact that the (final) lecture devoted to this quality remained unwritten. After reflecting on how consistency already plays a certain role…

Assuring the quality of education is a concern of learning institutions. To do so, it is necessary to have assertive learning management, with consistent data on students' outcomes. This research provides associate deans and researchers, a roadmap with which to gather evidence to improve the quality of open-ended assessments. Based on statistical…

Ofsted has frequently defended the judgements made during inspections by claiming that inspection ratings are reliable, as shown by the results from the collection of studies the inspectorate has conducted. I outline the inspectorate's view of reliability and problematise the studies that it has carried out, noting that these provide insufficient…

In this perspective, the authors critically examine "rater training" as it has been conceptualized and used in medical education. By "rater training," they mean the educational events intended to "improve" rater performance and contributions during assessment events. Historically, rater training programs have focused…

Retrospective confidence refers to the phenomenological experience of the level of certainty that retrieved information is, in fact, correct. Retrospective confidence judgments are examined across a range of sub-disciplines in psychology from perception to memory research, and in education and legal applications. This paper focuses on…

The limitations of Cohen's ? are reviewed and an alternative G-index is recommended for assessing nominal-scale agreement. Maximum likelihood estimates, standard errors, and confidence intervals for a two-rater G-index are derived for one-group and two-group designs. A new G-index of agreement for multirater designs is proposed. Statistical…

This paper has two aims. One is to draw a distinction between two types of trust. The other is to argue for its applicability in academic discourse on educational policies. One of the two types of trust is "ethical trust" that rests on beliefs about others' ethical virtues. The other is "institutional trust" that typically…

Focusing on systematic observation, one of the most potent methods of studying teaching quality, represents one of the numerous contributions of Daryl Siedentop to the profession. While he had a clear focus on issues of validity and reliability concerning systematic observation, over the past decades, attention to such issues appears to have…

We study the returns to experience in teaching, estimated using supervisor ratings from classroom observations. We describe the assumptions required to interpret changes in observation ratings over time as the causal effect of experience on performance. We compare two difference-in-differences strategies: the two-way fixed effects estimator common…

Higher education accreditation has spread internationally as a vehicle for quality assurance and improvement but is strongly influenced by accreditation practices in the United States. The organisational structure and processes of seven United States health professions accreditors were analysed to identify common characteristics that reflect…

The Educative Teacher Performance Assessment (edTPA) is a system of standardized portfolio assessments of teaching performance mandated for use by educator preparation programs in 18 states, and approved in 21 others, as part of initial certification for preservice teachers. Because of the high stakes involved for examinees, it is critical that…

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…

This paper aims to explore the philosophical theoretical foundations of two basic research paradigms, namely positivism and interpretivism. In the discussion process, literature in the relevant fields including academic papers and books is reviewed and used as support for the analysis. Firstly, the paper explores the differences between the…

Setting cutoff scores is one of the most common practices when using scales to aid in classification purposes. This process is usually done univariately where each optimal cutoff value is decided sequentially, subscale by subscale. While it is widely known that this process necessarily reduces the probability of "passing" such a test,…