Peter Schochet's guest appearances

Peter Schochet

Gov Innovator Podcast

Freeman Hrabowski

Jason Johnson

Tina Rosenberg

Peter Bergman

David Anderson

Robert Gordon

Booz Allen Hamilton

David Robbins

Raj Chetty

David Evans

Elizabeth Bell

Jonathan Ball

Lashawn Richburg-Hayes

Benjamin Castleman

Tom Kane

OwlTail

Public leaders — whether they’re helping run a state agency, a school system, a hospital, a set of Head Start centers or any other organization — are likely to implement changes over time, whether it’s adjusting programs or adding new services. Maybe it’s a new curriculum for students in a school district or new intake procedure for patients in a hospital. Whatever the change, how can those leaders determine if the change is actually effective? Our focus today is new software, called RCT-YES, designed to help public leaders (and the researchers who work with them) answer that question. It was funded by the Institute of Education Sciences, the statistics, research, and evaluation arm of the U.S. Department of Education, and developed in partnership with Mathematica Policy Research. The software, available free to download online, is based on new statistical methods for analyzing data from randomized controlled trials (RCTs). To learn more, we are joined by Peter Schochet. He is a nationally known methodological expert in program evaluation and a Senior Fellow at Mathematica. He led the team that developed RCT-YES. Web extra: For those with deeper expertise in evaluation, Peter Schochet gives an overview of how the RCT-YES software is designed to conduct a wide range of analyses using RCT or QED data and how the software uses new statistical methods for analyzing those data. [click here] The post Making rigorous program evaluation easier with RCT-YES software: An interview with Peter Schochet, Fellow, Mathematica Policy Research – Episode #137 appeared first on Gov Innovator Podcast.

Public leaders — whether they’re helping run a state agency, a school system, a hospital, a set of Head Start centers or any other organization — are likely to implement changes over time, whether it’s adjusting programs or adding new services. Maybe it’s a new curriculum for students in a school district or new intake procedure for patients in a hospital. Whatever the change, how can those leaders determine if the change is actually effective? Our focus today is new software, called <a href="https://www.rct-yes.com/" rel="nofollow" target="_blank">RCT-YES</a>, designed to help public leaders (and the researchers who work with them) answer that question. It was funded by the <a href="https://ies.ed.gov/" rel="nofollow" target="_blank">Institute of Education Sciences</a>, the statistics, research, and evaluation arm of the U.S. Department of Education, and developed in partnership with Mathematica Policy Research. The software, available free to download <a href="https://www.rct-yes.com/" rel="nofollow" target="_blank">online</a>, is based on new statistical methods for analyzing data from randomized controlled trials (RCTs). To learn more, we are joined by <a href="https://www.mathematica-mpr.com/our-people/staff/peter-schochet" rel="nofollow" target="_blank">Peter Schochet</a>. He is a nationally known methodological expert in program evaluation and a Senior Fellow at Mathematica. He led the team that developed RCT-YES. Web extra: For those with deeper expertise in evaluation, Peter Schochet gives an overview of how the RCT-YES software is designed to conduct a wide range of analyses using RCT or QED data and how the software uses new statistical methods for analyzing those data. [<a href="http://govinnovator.com/wp-content/uploads/2016/08/Peter-Schochet-RCT-YES-web-extra.mp3" rel="nofollow" target="_blank">click here</a>] The post <a href="https://govinnovator.com/rct-yes/" rel="nofollow" target="_blank">Making rigorous program evaluation easier with RCT-YES software: An interview with Peter Schochet, Fellow, Mathematica Policy Research – Episode #137</a> appeared first on <a href="https://govinnovator.com" rel="nofollow" target="_blank">Gov Innovator Podcast</a>.

Making rigorous program evaluation easier with RCT-YES software: An interview with Peter Schochet, Fellow, Mathematica Policy Research – Episode #137

How can public leaders and program managers track the performance of different sites within a program in a way that reflects impact — i.e., the value added of each site? The most rigorous approach is to run a rigorous program evaluation, such as a randomized controlled trial, by site, but that type of evaluation is not always feasible. Another approach (the most common one) is to use performance measures, since they are low-cost and easy to implement, but there’s a downside: They aren’t necessarily good indicators of impact. That’s because the performance of sites are effected by local conditions and demographics, not just program quality. Our interview focuses on public leaders can design performance measures to better reflect impact, including through the use of regression-adjusted performance measures — that is, measures that statistically control for factors that aren’t related to program quality. We get insights from Peter Schochet. He’s a Senior Fellow at Mathematica Policy Research, a leading authority on evaluation methodology, and the co-author of an article in the Journal of Policy Analysis and Management on this topic. In the interview, he describes how regression-adjusted performance measures can be useful, especially if there is good baseline data, measures are not overly complex and align well with the most relevant outcomes of interest, and (when relevant) if there is longer-term follow-up data. The post How to design performance measures to better measure impact: An interview with Peter Schochet, Senior Fellow, Mathematica Policy Research – Episode #94 appeared first on Gov Innovator podcast.

How can public leaders and program managers track the performance of different sites within a program in a way that reflects impact — i.e., the value added of each site? The most rigorous approach is to run a rigorous program evaluation, such as a randomized controlled trial, by site, but that type of evaluation is not always feasible. Another approach (the most common one) is to use performance measures, since they are low-cost and easy to implement, but there’s a downside: They aren’t necessarily good indicators of impact. That’s because the performance of sites are effected by local conditions and demographics, not just program quality. Our interview focuses on public leaders can design performance measures to better reflect impact, including through the use of regression-adjusted performance measures — that is, measures that statistically control for factors that aren’t related to program quality. We get insights from <a href="http://www.mathematica-mpr.com/our-people/staff/peter-schochet" rel="nofollow" target="_blank">Peter Schochet</a>. He’s a Senior Fellow at Mathematica Policy Research, a leading authority on evaluation methodology, and the co-author of an <a href="http://onlinelibrary.wiley.com/doi/10.1002/pam.21746/abstract" rel="nofollow" target="_blank">article</a> in the Journal of Policy Analysis and Management on this topic. In the interview, he describes how regression-adjusted performance measures can be useful, especially if there is good baseline data, measures are not overly complex and align well with the most relevant outcomes of interest, and (when relevant) if there is longer-term follow-up data. The post <a href="https://govinnovator.com/schochet/" rel="nofollow" target="_blank">How to design performance measures to better measure impact: An interview with Peter Schochet, Senior Fellow, Mathematica Policy Research – Episode #94</a> appeared first on <a href="https://govinnovator.com" rel="nofollow" target="_blank">Gov Innovator podcast</a>.

How to design performance measures to better measure impact: An interview with Peter Schochet, Senior Fellow, Mathematica Policy Research – Episode #94