The Campbellian validity typology has been used as a foundation for outcome evaluation and for developing evidence-based interventions for decades. As such, randomized control trials were preferred for outcome evaluation. However, some evaluators disagree with the validity typology's argument that randomized controlled trials as the best design…

Many autistic children access some form of early intervention, but little is known about the value for money of different programs. We completed a scoping review of full economic evaluations of early interventions for autistic children and/or their families. We identified nine studies and reviewed their methods and quality. Most studies involved…

Analysis of symmetrically predicted endogenous subgroups (ASPES) is an approach to assessing heterogeneity in an ITT effect from a randomized experiment when an intermediate variable (one that is measured after random assignment and before outcomes) is hypothesized to be related to the ITT effect, but is only measured in one group. For example,…

This article offers a case example of how experimental evaluation methods can be coupled with principles of design-based implementation research (DBIR), improvement science (IS), and rapid-cycle evaluation (RCE) methods to provide relatively quick, low-cost, credible assessments of strategies designed to improve programs, policies, or practices.…

Education decisionmakers need access to the best evidence about the effectiveness of education interventions, including practices, products, programs, and policies. It can be difficult, time consuming, and costly to access and draw conclusions from relevant studies about the effectiveness of interventions. The What Works Clearinghouse (WWC)…

In this response, we first show that Simpson's proposed analysis answers a different and less interesting question than ours. We then justify the choice of prior for our Bayes factors calculations, but we also demonstrate that the substantive conclusions of our article are not substantially affected by varying this choice.

Given the widespread use of non-experimental (NE) methods for assessing program impacts, there is a strong need to know whether NE approaches yield causally valid results in field settings. In within-study comparison (WSC) designs, the researcher compares treatment effects from an NE with those obtained from a randomized experiment that shares the…

A recent paper uses Bayes factors to argue a large minority of rigorous, large-scale education RCTs are "uninformative." The definition of "uninformative" depends on the authors' hypothesis choices for calculating Bayes factors. These arguably overadjust for effect size inflation and involve a fixed prior distribution,…

This report presents findings from exploratory, descriptive meta-analyses of effect sizes reported by the first 82 EEF evaluations that used a randomised controlled trial (RCT) or clustered RCT impact evaluation design published up to January 2019. The review used a theoretical framework derived from literature with five overarching themes to…

This document summarises key findings from the quantitative strands of a review of the Education Endowment Foundation (EEF) evaluations that had reported from the establishment of EEF in 2011 up to January 2019. The quantitative strands summarised include meta-analyses of effect sizes reported for attainment outcomes and descriptive analyses of…

This document provides supplementary statistical tables to support the review of Education Endowment Foundation (EEF) evaluations. This includes: (1) Descriptive (univariate) tables for all explanatory variables; (2) Tables for the meta-analyses of primary ITT effect sizes; (3) Tables for the meta-analyses of secondary ITT effect sizes; (4) Tables…

Evaluating the impact of complex whole-school interventions (CWSIs) is challenging. However, what evidence there is suggests that school leadership and other elements of whole-school contexts are important for pupils' attainment (Leithwood et al., 2006), suggesting that interventions aimed at changing these have significant potential to improve…

There's a strong case for making social and emotional learning (SEL) skills and competencies a central feature of elementary school. Children who master SEL skills get along better with others, do better in school, and have more successful careers and better mental and physical health as adults. Evidence from the most rigorous studies of…

Design-based methods have recently been developed as a way to analyze data from impact evaluations of interventions, programs, and policies. The impact estimators are derived using the building blocks of experimental designs with minimal assumptions, and have good statistical properties. The methods apply to randomized controlled trials (RCTs) and…

A new design-based theory has recently been developed to estimate impacts for randomized controlled trials (RCTs) and basic quasi-experimental designs (QEDs) for a wide range of designs used in social policy research (Imbens & Rubin, 2015; Schochet, 2016). These methods use the potential outcomes framework and known features of study designs…