Explore the vast range of titles available.

Regression discontinuity (RD) designs have gained significant popularity as a quasi-experimental device for evaluating education programs and policies. In this paper, we present a comprehensive review of RD designs, focusing on the continuity-based framework, the most widely adopted RD framework. We first review the fundamental aspects of RD designs, drawing on potential outcomes and causal graphs. We then discuss the validity threats in RD designs, including manipulation, discreteness of the running variable, statistical power, and generalizability. Additionally, we provide an overview of the existing extensions to RD designs. To exemplify the application of RD methods, we analyze the effect of New Jersey’s pre-kindergarten program on children’s vocabulary test scores, using an educational dataset. Finally, we offer practical guidelines in the conclusion to promote the appropriate use of RD methods in educational research.

Recently, machine learning (ML) methods have been used in causal inference to estimate treatment effects in order to reduce concerns for model mis-specification. However, many ML methods require that all confounders are measured to consistently estimate treatment effects. In this paper, we propose a family of ML methods that estimate treatment effects in the presence of cluster-level unmeasured confounders, a type of unmeasured confounders that are shared within each cluster and are common in multilevel observational studies. We show through simulation studies that our proposed methods are robust from biases from unmeasured cluster-level confounders in a variety of multilevel observational studies. We also examine the effect of taking an algebra course on math achievement scores from the Early Childhood Longitudinal Study, a multilevel observational educational study, using our methods. The proposed methods are available in the CURobustML R package.

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 well-established finite mixture/latent class models. This article proposes a hybrid method, a combination of finite mixture modeling and ML methods from causal inference to discover effect heterogeneity in latent classes. Our simulation study reveals that hybrid ML methods produced more precise and accurate estimates of treatment effects in latent classes. We also use hybrid ML methods to estimate the differential effects of private lessons across latent classes from Trends in International Mathematics and Science Study data.

Optimal treatment regimes (OTRs) have been widely employed in computer science and personalized medicine to provide data-driven, optimal recommendations to individuals. However, previous research on OTRs has primarily focused on settings that are independent and identically distributed, with little attention given to the unique characteristics of educational settings, where students are nested within schools and there are hierarchical dependencies. The goal of this study is to propose a framework for designing OTRs from multisite randomized trials, a commonly used experimental design in education and psychology to evaluate educational programs. We investigate modifications to popular OTR methods, specifically Q-learning and weighting methods, in order to improve their performance in multisite randomized trials. A total of 12 modifications, 6 for Q-learning and 6 for weighting, are proposed by utilizing different multilevel models, moderators, and augmentations. Simulation studies reveal that all Q-learning modifications improve performance in multisite randomized trials and the modifications that incorporate random treatment effects show the most promise in handling cluster-level moderators. Among weighting methods, the modification that incorporates cluster dummies into moderator variables and augmentation terms performs best across simulation conditions. The proposed modifications are demonstrated through an application to estimate an OTR of conditional cash transfer programs using a multisite randomized trial in Colombia to maximize educational attainment.

Purpose: The aim of this study was to determine how the speech disorder profiles in Down syndrome (DS) relate to reduced intelligibility, atypical overall quality, and impairments in the subsystems of speech production (phonation, articulation, resonance, and prosody). Method: Auditory-perceptual ratings of intelligibility, overall quality, and features associated with the subsystems of speech production were obtained from recordings of 79 children and adults with DS. Ratings were made for sustained vowels (62 of 79 speakers) and short sentences (79 speakers). The data were analyzed to determine the severity of the affected features in each speaking task and to detect patterns in the group data by means of principal components analysis. Results: Reduced intelligibility was noted in 90% of the speakers, and atypical overall speech quality was noted in 100%. Affected speech features were distributed across the speech production subsystems. Principal components analysis revealed four components each for the vowel and sentence tasks, showing that individuals with DS are not homogeneous in the features of their speech disorder. Discussion: The speech disorder in DS is complex in its perceptual features and reflects impairments across the subsystems of speech production, but the pattern is not uniform across individuals, indicating that attention must be given to individual variation in designing treatments.

Researchers often assess causal effects of educational programs or policies using educational assessment data. This dissertation explores novel methods of estimating causal effects in educational assessment data and is broken into three parts. The first part proposes a regression discontinuity design with an ordinal running variable to assess the effects of extended time accommodations for the National Assessment of Educational Progress. The second part investigates how to enhance the performance of machine learning methods to estimate causal effects in multilevel observational data. The third part discusses how to estimate effect heterogeneity that arises from unobservable, latent characteristics by using machine-learning -based methods for causal inference. Overall, the methods from each part provide investigators with modern tools to estimate causal effects in increasingly large and complex educational assessment data.

There is limited information on how patient outcomes have changed during the COVID-19 pandemic. This study characterizes changes in mortality, intubation, and ICU admission rates during the first 20 months of the pandemic. University of Wisconsin researchers collected and harmonized electronic health record data from 1.1 million COVID-19 patients across 21 United States health systems from February 2020 through September 2021. The analysis comprised data from 104,590 adult hospitalized COVID-19 patients. Inclusion criteria for the analysis were: (1) age 18 years or older; (2) COVID-19 ICD-10 diagnosis during hospitalization and/or a positive COVID-19 PCR test in a 14-day window (+/- 7 days of hospital admission); and (3) health system contact prior to COVID-19 hospitalization. Outcomes assessed were: (1) mortality (primary), (2) endotracheal intubation, and (3) ICU admission. The 104,590 hospitalized participants had a mean age of 61.7 years and were 50.4% female, 24% Black, and 56.8% White. Overall risk-standardized mortality (adjusted for age, sex, race, ethnicity, body mass index, insurance status and medical comorbidities) declined from 16% of hospitalized COVID-19 patients (95% CI: 16% to 17%) early in the pandemic (February-April 2020) to 9% (CI: 9% to 10%) later (July-September 2021). Among subpopulations, males (vs. females), those on Medicare (vs. those on commercial insurance), the severely obese (vs. normal weight), and those aged 60 and older (vs. younger individuals) had especially high mortality rates both early and late in the pandemic. ICU admission and intubation rates also declined across these 20 months. Mortality, intubation, and ICU admission rates improved markedly over the first 20 months of the pandemic among adult hospitalized COVID-19 patients although gains varied by subpopulation. These data provide important information on the course of COVID-19 and identify hospitalized patient groups at heightened risk for negative outcomes. ClinicalTrials.gov Identifier: NCT04506528 (https://clinicaltrials.gov/ct2/show/NCT04506528).

This is an invited commentary on the Psychometrika focus article \"Fairness Issues and Evaluation in Psychometrics and AI/ML: What Can We Learn from Each Field?\" by Ying Cheng (2026, doi:10.1017/psy.2026.10110). Cheng offers a systematic comparison between long-standing test fairness and modern algorithmic fairness. Her mapping of the entire testing workflow onto the AI/ML fairness paradigm, rather than only the final selection stage, is a crucial contribution to interdisciplinary fairness research. This commentary extends her discussion by examining two conceptual issues: the distinction between equality and equity, and the role of causality in fairness research. Together, the focus article and this commentary point to directions for future fairness research across the psychometrics and AI/ML communities.

Robins and Richardson (2010) reformulated mediation analysis by decomposing treatments into multiple components and examining separable effects of each component. While this approach is increasingly popular, existing work has analyzed ``two-arm'' data, where components are strictly bundled and manipulated simultaneously. However, in practice, four-arm data where components are assigned independently are often available. For example, testing accommodations might strictly bundle extra time with a separate session or allow them to be assigned separately. To address this distinction, we propose a general framework for analyzing separable effects in four-arm and two-arm designs. This framework provides distinct identification and estimation strategies for each design. For estimation, we utilize efficient influence function estimators coupled with machine learning and cross-fitting techniques. Additionally, we introduce two falsification tests for key identification assumptions required in the two-arm design by leveraging four-arm data. We investigate the performance of the proposed estimators via a simulation study and demonstrate their application by studying the effect of extended time accommodations using data from the National Assessment of Educational Progress. Ultimately, this separable effects analysis enables practitioners to clearly communicate underlying mechanisms and derive informative policy recommendations.

Differential item functioning (DIF) is a widely used statistical notion for identifying items that may disadvantage specific groups of test-takers. These groups are often defined by non-manipulable characteristics, e.g., gender, race/ethnicity, or English-language learner (ELL) status. While DIF can be framed as a causal fairness problem by treating group membership as the treatment variable, this invokes the long-standing controversy over the interpretation of causal effects for non-manipulable treatments. To better identify and interpret causal sources of DIF, this study leverages an interventionist approach using treatment decomposition proposed by Robins and Richardson (2010). Under this framework, we can decompose a non-manipulable treatment into intervening variables. For example, ELL status can be decomposed into English vocabulary unfamiliarity and classroom learning barriers, each of which influences the outcome through different causal pathways. We formally define separable DIF effects associated with these decomposed components, depending on the absence or presence of item impact, and provide causal identification strategies for each effect. We then apply the framework to biased test items in the SAT and Regents exams. We also provide formal detection methods using causal machine learning methods, namely causal forests and Bayesian additive regression trees, and demonstrate their performance through a simulation study. Finally, we discuss the implications of adopting interventionist approaches in educational testing practices.