• MDRC Publications


      Lessons Learned from Career Pathways and Child First

      October, 2022
      Samantha Xia, Camille Préel-Dumas, Kristin Porter

      Social services programs are increasingly looking to forecast which participants are likely to reach major milestones. Some explore advanced predictive modeling, but the Center for Data Insights (CDI) has found that such methods come with trade-offs. This post outlines CDI’s approach to predictive analytics, using illustrations from two studies.

      June, 2022
      Kristin Porter, Zarni Htet, Kristen Hunter, Luke Miratrix

      Multiple testing procedures reduce the likelihood of false positive findings, but can also reduce the probability of detecting true effects. This post introduces two open-source software tools from the Power Under Multiplicity Project that can help researchers plan analyses for randomized controlled trials using multiple testing procedures.


      Evidence from Child First

      May, 2022

      This brief presents results from a proof-of-concept exercise that examined the potential benefits of using predictive analytics to improve service delivery by Child First, a program that provides therapeutic support to families with young children. The information may be useful for other organizations interested in implementing these cutting-edge tools.

      May, 2020
      Kristin Porter, Cindy Redcross, Luke Miratrix

      Pretrial release and detention decisions for defendants are increasingly guided by risk assessments guided by data, which are intended to counteract biases but have the potential to introduce new biases and perpetuate racial disparities. This research brief describes the approach taken by MDRC to understand, assess, and address these biases.

      November, 2017
      Kristin Porter

      Assessing an intervention’s effects on multiple outcomes increases the risk of false positives. Procedures that make adjustments to address this risk can reduce power, or the probability of detecting effects that do exist. MDRC’s Reflections on Methodology discusses how to estimate power when making adjustments as well as alternative definitions of power.

      Issue Focus
      September, 2017
      Rekha Balu, Kristin Porter

      As organizations increase their use of sophisticated screening and risk assessments in their decision making, the results have the potential to fundamentally change practice, organizational culture, and the structure of work. Implementation researchers can inform the use of predictive analytic tools both before and after their adoption.

      September, 2017
      Kristin Porter, Rekha Balu, Richard Hendra

      Machine learning algorithms, when combined with the contextual knowledge of researchers and practitioners, offer service providers nuanced estimates of risk and opportunities to refine their efforts. The first post of a new series, Reflections on Methodology, discusses how MDRC helps organizations make the most of predictive modeling tools.


      Results from a Partnership Between New Visions for Public Schools and MDRC

      November, 2016
      Rekha Balu, Kristin Porter, Brad Gunton

      A custom-designed intervention aimed to improve New York City high school students’ attendance by using text messaging to send parents daily absence updates and weekly attendance summaries. The rapid-turnaround randomized evaluation found that the short-term intervention did not improve attendance rates during the second semester of the 2015-2016 school year.


      A Primer for Researchers Working with Education Data

      November, 2016
      Kristin Porter, Rekha Balu

      Predictive modeling estimates individuals’ probabilities of future outcomes by building and testing a model using data on similar individuals whose outcomes are already known. The method offers benefits for continuous improvement efforts and efficient allocation of resources. This paper explains MDRC’s framework for using predictive modeling in education.


      A Guide for Researchers

      July, 2016
      Kristin Porter

      Conducting multiple statistical hypothesis tests can lead to spurious findings of effects. Multiple testing procedures (MTPs) counteract this problem but can substantially change statistical power. This paper presents methods for estimating multiple definitions of power and presents empirical findings on how power is affected by the use of MTPs.


      Lessons from a Simulation Study

      November, 2014
      Kristin Porter, Sean F. Reardon, Fatih Unlu, Howard Bloom, Joseph P. Robinson-Cimpian

      This paper makes valuable contributions to the literature on multiple-rating regression discontinuity designs (MRRDDs). It makes concrete recommendations for choosing among existing MRRDD estimation methods, for implementing any chosen method using local linear regression, and for providing accurate statistical inferences.


      Elementary Student Achievement and the Bay Area School Reform Collaborative’s Focal Strategy

      December, 2006
      Kristin Porter, Jason Snipes

      The Bay Area School Reform Collaborative’s focal strategy, a system-wide reform that coaches district and school leaders, supports evidence-based decision-making, and promotes networking within and among schools, has no strong association with changes in elementary student achievement.


      Elementary Student Achievement and the Bay Area School Reform Collaborative’s Focal Strategy

      February, 2006
      Kristin Porter, Jason Snipes, Jean Eisberg

      The Bay Area School Reform Collaborative’s strategy seeks to raise student achievement in six elementary school districts in the San Francisco Bay Area by coaching supervisors, principals, and teachers, instituting evidence-based decision making, and promoting sharing of experiences among schools. During the first two years of implementation, MDRC found no strong, pervasive association with student achievement.

      Working Paper

      Evidence from a Sample of Recent CET Applicants

      September, 2005
      Cynthia Miller, Kristin Porter

      This working paper examines employment and earnings over a four-year period for a group of disadvantaged out-of-school youth who entered the Evaluation of the Center for Employment Training (CET) Replication Sites between 1995 and 1999. It assesses the importance of three key factors as barriers to employment: lack of a high school diploma, having children, and having an arrest record.


      Final Report on the Center for Employment Training Replication Sites

      September, 2005
      Cynthia Miller, Johannes Bos, Kristin Porter, Fannie M. Tseng, Yasuyo Abe

      The Center for Employment Training (CET) in San Jose, California, produced large, positive employment and earnings effects for out-of-school youth in the late 1980s. However, in this replication study, even the highest-fidelity sites did not increase employment or earnings for youth over the 54-month follow-up period, despite short-term positive effects for women.


      A Study of Adult Student Persistence in Library Literacy Programs

      January, 2005
      Kristin Porter, Sondra Cuban, John P. Comings

      Library-based literacy programs face serious challenges to improving adult students’ participation. This study suggests programs should be prepared to accommodate intermittent participation by adult students and to connect students to social services and other supports.


      Thirty-Month Findings from the Evaluation of the Center for Employment Training Replication Sites

      June, 2003
      Cynthia Miller, Johannes Bos, Kristin Porter, Fannie M. Tseng, Fred Doolittle, Deana Goldsmith, Mary P. Vencill

      Efforts to replicate the experience of the Center for Employment Training in San Jose, California — a uniquely successful program that helped at-risk youth develop skills needed to compete in today’s labor market — showed mixed results.


      Responding to the Challenges of Adult Student Persistence in Library Literacy Programs

      April, 2003
      John P. Comings, Sondra Cuban, Johannes Bos, Kristin Porter

      Based on a study of nine adult literacy programs in public libraries, this report examines student characteristics, participation patterns, and new strategies to raise student persistence.

  • Other Publications

  • Projects