This study demonstrates how to evaluate a university-wide online course designed to support student transition into university by using Propensity Score Matching (PSM) and Doubly Robust Estimation (DRE). Using data from seven academic years, from 2016/17 to 2022/23, with more than 28,000 students, we examine whether enrolment in this optional…

We study the external validity of instrumental variable estimation. The key assumption we impose for external validity is conditional external unconfoundedness among compliers, which means that the treatment effect and target selection are independent among compliers conditional on covariates. We study this assumption with a case study about the…

Evidence-based education aims to support policy makers choosing between potential interventions. This rarely involves considering each in isolation; instead, sets of evidence regarding many potential policy interventions are considered. Filtering a set on any quantity measured with error risks the "winner's curse": conditional on…

The aim of the current study is to estimate the graduation grade point average (GPA) at the Arab International University (AIU). The importance of this study is that it is the first of its kind in Syria, particularly under the conditions of the bitter war, which has not yet come to its end. The sample of the study consists of data collected from…

The Mantel-Haenszel estimator is one of the most popular techniques for measuring differential item functioning (DIF). A generalization of this estimator is applied to the context of DIF to compare items by taking the covariance of odds ratio estimators between dependent items into account. Unlike the Item Response Theory, the method does not rely…

In this paper is proposed a straightforward model selection approach that indicates the most suitable count regression model based on relevant data characteristics. The proposed selection approach includes four of the most popular count regression models (i.e. Poisson, negative binomial, and respective zero-inflated frameworks). Moreover, it…

The study was carried out with 45 web pages reached as a result of scanning the relevant keywords in the 'Google' search engine, eliminating repetitive web pages, and applying the inclusion and exclusion criteria. Content analysis, readability calculation, and statistical analyses of the data obtained from web-based information sources were…

This article discusses the estimation of a population proportion, using the auxiliary information available, which is incorporated into the estimation procedure by a probit model fit. Three probit regression estimators are considered, using model-based and model-assisted approaches. The theoretical properties of the proposed estimators are derived…

The ability of universities and colleges to predict the success of admitted students continues to be a key concern of higher education officials. Apart from a desire to see students have successful academic careers, there is also the fiscal reality of greater tuition revenues providing needed support for university budgets. Using administrative…

Humans and other animals are able to make rough estimations of quantities using what has been termed the "approximate number system" (ANS). Much evidence suggests that sensitivity to numerosity correlates with symbolic math capacity, leading to the suggestion that the ANS may serve as a start-up tool to develop symbolic math. Many…

We investigate the reliability of data from the Wage Indicator (WI), the largest online survey on earnings and working conditions. Comparing WI to nationally representative data sources for 17 countries reveals that participants of WI are not likely to have been representatively drawn from the respective populations. Previous literature has…

A readily applicable procedure is discussed that allows evaluation of the discrepancy between the popular coefficient alpha and the reliability coefficient of a scale with second-order factorial structure that is frequently of relevance in empirical educational and psychological research. The approach is developed within the framework of the…

The hierarchical model of van der Linden is the most popular model for responses and response times in tests. It is composed of two separate submodels--one for the responses and one for the response times--that are joined at a higher level. The submodel for the response times is based on the lognormal distribution. The lognormal distribution is a…

There has been increasing interest in exploring heterogeneous treatment effects using machine learning (ML) methods such as causal forests, Bayesian additive regression trees, and targeted maximum likelihood estimation. However, there is little work on applying these methods to estimate treatment effects in latent classes defined by…

Numerous studies have investigated economies of scale and scope in higher education as a means of providing public and private providers of college and university teaching, research and other services and their stakeholders with knowledge of the cost structures that underpin provision in this economically and socially important sector. However,…