Missing data are a pervasive problem in data analysis. Three common methods for addressing the problem are (a) complete-case analysis, where only units that are complete on the variables in an analysis are included; (b) weighting, where the complete cases are weighted by the inverse of an estimate of the probability of being complete; and (c)…

Educational assessment is used throughout the world for a range of different formative and summative purposes. Wherever an assessment is developed, whether by a teacher creating a quiz for their class, or by a testing company creating a high stakes assessment, it is necessary to decide how long the test should be. Specifically, how many questions…

Since its introduction in 2017, NFER has been contracted by Ofqual to develop, deliver and analyse the results of the National Reference Test (NRT) in English and Maths. The NRT is administered annually and shows if student performance in English and maths at GCSE level has changed from year-to-year. This year, more than 13,000 Year 11 students…

Using rich longitudinal data from the UK's Millennium Cohort Study (MCS), the authors compare the performance of private and state school pupils in age 16 national examinations (GCSEs) in England, where private schools are particularly well resourced by international standards. Performance among pupils attending private secondary schools is…

Since its introduction in 2017, NFER has been contracted by Ofqual to develop, deliver and analyse the results of the National Reference Test (NRT) in English and maths. The NRT is administered annually and shows if student performance in English and maths at GCSE level has changed from year-to-year. This year, more than 13,000 Year 11 students…

Since its introduction in 2017, NFER has been contracted by Ofqual to develop, deliver and analyse the results of the National Reference Test (NRT) in English and maths. The NRT is administered annually and shows if student performance in English and maths at GCSE level has changed from year-to-year. This year, around 13,000 Year 11 students from…

Administrative data are increasingly being used to study inequalities in education. Yet a well-known difficulty with such resources is the limited information they hold. A commonly used proxy for children coming from a low-income background is their eligibility for free school meals, yet this is likely to be of little use in measuring academic…

On average, groups of autistic individuals are more likely than groups of non-autistic individuals to exhibit unconventional conversational behaviours. We examined autistic and non-autistic children's social impressions of unconventional responding, as well as actual conversational behaviours in the same participants. Across two studies, 36…

This article illustrates how a new framework for conceptualising comparability has the potential to help assessment professionals to understand and to conduct debate on linking theory and practice. The framework was used as a lens through which to study a corpus of research reports, from which a narrative was constructed to characterise the…

The concept of moderate learning difficulties (MLD) is not clearly understood in its definition and in its general use. Nevertheless, as a distinct area of special educational needs (SEN) this category has constituted about a quarter of all of those pupils identified as having SEN in England. This paper reports the analysis of findings from an…

Background: Successfully selecting students for undergraduate courses and for teaching is notoriously difficult. Traditionally, in England, A level grades and interviews have been used in conjunction with a variety of other approaches. Purpose: This paper examines the predictive validity of students' A level grades and of scores from a structured…

This paper builds upon an earlier analysis presented in this journal. Using official figures for school compositions and for outcomes at KS4 from 1997 to 2007, this paper considers each of the annual cohorts of new Academies in England, from 2002 to 2006. It shows that their level of success in comparison to their predecessors, national averages,…

This paper explores gender differential performance in "gifted and talented" 9- and 13-year-olds in a mathematics assessment in England. Boys' and girls' attitudes to mathematics and their views about which gender is better at mathematics are also considered. The study employs the use of a matched sample of boys and girls so that school,…

This paper reports analysis of 2006-2007 on-entry assessment data from the Performance Indicators in Primary Schools Baseline Assessment (PIPS-BLA) of random samples of students in England, Scotland, New Zealand and Australia. The analysis aimed, first, to investigate the validity and reliability of that instrument across countries and sexes, and,…

This article explores the effect on assessment of "translating" paper and pencil test items into their computer equivalents. Computer versions of a set of mathematics questions derived from the paper-based end of key stage 2 and 3 assessments in England were administered to age appropriate pupil samples, and the outcomes compared.…