Search results

Relative to the randomized controlled trial (RCT), the basic regression discontinuity (RD) design suffers from lower statistical power and lesser ability to generalize causal estimates away from the treatment eligibility cutoff. This chapter seeks to mitigate these limitations by adding an untreated outcome comparison function that is measured along all or most of the assignment variable. When added to the usual treated and untreated outcomes observed in the basic RD, a comparative RD (CRD) design results. One version of CRD adds a pretest measure of the study outcome (CRD-Pre); another adds posttest outcomes from a nonequivalent comparison group (CRD-CG). We describe how these designs can be used to identify unbiased causal effects away from the cutoff under the assumption that a common, stable functional form describes how untreated outcomes vary with the assignment variable, both in the basic RD and in the added outcomes data (pretests or a comparison group’s posttest). We then create the two CRD designs using data from the National Head Start Impact Study, a large-scale RCT. For both designs, we find that all untreated outcome functions are parallel, which lends support to CRD’s identifying assumptions. Our results also indicate that CRD-Pre and CRD-CG both yield impact estimates at the cutoff that have a similarly small bias as, but are more precise than, the basic RD’s impact estimates. In addition, both CRD designs produce estimates of impacts away from the cutoff that have relatively little bias compared to estimates of the same parameter from the RCT design. This common finding appears to be driven by two different mechanisms. In this instance of CRD-CG, potential untreated outcomes were likely independent of the assignment variable from the start. This was not the case with CRD-Pre. However, fitting a model using the observed pretests and untreated posttests to account for the initial dependence generated an accurate prediction of the missing counterfactual. The result was an unbiased causal estimate away from the cutoff, conditional on this successful prediction of the untreated outcomes of the treated.

In this chapter, we first describe the all governing principles of treatment for sexual offenders that maximise effectiveness. These are derived from Andrews and Bonta's (2006) summary of a variety of meta-analyses of outcome studies. From this source and others, we then claim that there are three elements essential to effective treatment: (1) targeting criminogenic features; (2) employing empirically sound procedures to modify these targets; and (3) delivering treatment in an effective psychotherapeutic way. Next we describe our treatment approach that emphasises these crucial elements within a strength-based programme that is motivational and provides Ward's (2002) Good Lives Model as the framework. We then challenge the broadly accepted idea that the Random Controlled Trial (RCT) is the only basis upon which inferences about treatment effectiveness can be derived. We point to methodological, practical and ethical problems associated with implementing an RCT study and offer at least two alternatives: the so-called ‘incidental design’ which compares the outcome of the treated group with a matched (but not randomly assigned) group from the same or similar setting to the treated group; and a strategy where the recidivism rate of treated group is compared with what would be expected on the basis of risk assessments of each of the treated subjects.

In this chapter, I examine the properties of four realized correlation estimators and model their jumps. The correlations are between the three main FTSE indices of the Athens Stock Exchange. Using intraday data I first construct four state-of-the-art realized correlation estimators which I then use in testing for normality, long memory, asymmetries and jumps and also in modelling for jumps. Jumps are detected when the realized correlation is higher than 0.99 and lower than 0.01 in absolute values. Then the realized correlation is modelled with the simple heterogeneous autoregressive (HAR) model and the HAR model with jumps (HAR-J). This is the first time, to the best of my knowledge, that the realized correlation between the three indices for the Greek equity market is examined.

Psychotherapy is perhaps the most known and identifiable with one of the field’s originators Sigmond Freud who is often accredited as being the inventor of the talking cure. However, it was many decades after psychoanalysis was first used by Freud that robust research and evidence was applied to psychotherapy, and its findings used to support practice in various contexts. While psychoanalysis is still practiced, the field has moved on and includes many hundreds if not thousands of approaches to healing. What has not improved, in general, is the between school rivalry regarding the efficacy and effectiveness of the different approaches. While it is now accepted that in general terms all approaches are about equally effective, certain research is often provided with more legitimacy than others. Mainly, the randomised control trial (RCT) is considered the gold standard in research terms, especially when it comes to establishing the efficacy and effectiveness of different psychotherapies. Empirically supported treatments (ESTs) are in prime position to take advantage of these political decisions, and this chapter will introduce the reader to these debates.

With the national emphasis on the use of evidence-based practices in educational settings, intervention research within the field of special education is being scrutinized. No Child Left Behind (NCLB) has defined evidence-based practices primarily by research that is based on quantitative, experimental designs (i.e., RCT). Although the use of appropriate experimental designs has an important place in educational research, defining evidence-based practices based on research design alone is limiting. One critical aspect of research that has not received much attention is the importance of rigorous and precise measurement and systematic replication of research findings. The purpose of this chapter is to review issues surrounding measurement and its effect on validity in intervention research in the field of behavioral disorders. Specifically, we discuss how more rigorous measurement can positively influence the internal, external, construct, and social validity of research findings. A review of current trends in behavioral disorders intervention research is discussed as well as implications for future research.

This chapter explores the methods developed to improve STEM success for students at two public urban institutions, a project whose aim is to improve academic outcomes for undergraduate students, especially for those most vulnerable and least likely to succeed in this student population. The theory of change that underpins the project – including its activities and its evaluation plan – posits that three interlocked activities (course redesign, peer mentors and articulation) will lead to improvements in academic outcomes and ultimately contribute to the overarching goal of increasing the number of students from underserved backgrounds who graduate with baccalaureate STEM degrees. The project focusses on the first courses students take in STEM, where they are also most likely to fail. We describe the methodology developed for faculty development and the organizational structure of the peer mentoring component for these courses. Both of these components constitute safe spaces where faculty and peer mentors learn to support students using evidence-based and inclusive instructional practices. Courses redesigned by faculty were offered following a cluster-level randomized control trial design, where sections were assigned to treatment (with or without a peer) or control. These interventions have a positive impact on cumulative GPA, according to preliminary analyses. The project also has a positive effect on faculty participants and on peer mentors, both groups now better prepared to jointly deliver STEM curricula in more effective ways. Among the reasons why this works, instructor empathy surfaces as playing a leading role in academic outcomes for undergraduate students.

The chapter considers the change of position of the Home Office on the value of randomised controlled trials (RCTs) in England and Wales which took place around 2003 after the end of the Crime Reduction Programme (CRP). Before the CRP Home Office researchers had shown little interest in RCTs; after it, they came close to arguing that no other kinds of evaluation research were worth doing. This represented a reversal of a position that had dominated Home Office thinking on the issue for almost 30 years – that RCTs were in general impractical and unlikely to produce clear-cut results. This view was based in part on the experience of RCTs in the 1970s, which led influential researchers to conclude that the method could not be transferred from medicine to criminal justice. But, disappointed with the lack of definite results from the CRP, the Home Office turned back to RCTs as a potential source of certainty about what works. The chapter considers two recent scholarly exchanges on the question, in relation to an evaluation of a community crime reduction programme, for which an experimental design was attempted but not achieved, and to Lawrence Sherman's recent advocacy of RCTs and his use of research on restorative justice as an example of the successful use of the method. The chapter argues that the restorative justice research, while of very high quality, does not provide as clear an example of the use of an RCT as Sherman claims, and concludes with some reflections on the inherent difficulties of criminal justice evaluation, and on the lack of a predictable, rational relationship between research quality and policy influence.

In this chapter, we examined issues related to research design and research management as applied to scientific research conducted in applied school settings. In terms of research design, randomized controlled trials (RCTs) have an important role to play in advancing a scientific agenda for school-based research. However, given their enormous cost and complexity, it is important to carefully time their implementation in the development cycle. We suggested that the use of RCTs is most appropriate in the later stages of the development cycle when the focus is on demonstrating the efficacy and/or effectiveness of an intervention and establishing its generalizability under the real world conditions of schooling. We also recommended establishing a hierarchy of evidence for an intervention that involves implementing a cost-efficient mix of single case, quasi-experimental, and true experimental designs where appropriate and feasible. In examining issues related to the management of research and the implementation of a knowledge development agenda for schools, it has become apparent that treatment integrity is a keystone variable. We discussed the importance of treatment integrity, with attention to the impact on internal and external validity. Finally, we offered practical considerations to support high-quality, respectful school-based inquiry.