Search

Supplemental material for Variance Estimation in Evaluations With No-Shows: A Comparison of Methods by Daniel Litwok and Laura R. Peck in American Journal of Evaluation

Prior work has analyzed the extent to which welfare recipients engage in giving money and time to charitable causes (Brooks, 2002, 2004; Author4 & Author1, 2009; Author1 & Author4, 2011), finding that public assistance is negatively associated with donating money with the relationship to volunteering being unclear. Nevertheless, sticky issues of selection bias compel more deliberate thinking about the strength of assertions about cause and effect. In response, we now conduct a multivariate cluster-based subgroup analysis approach to more confidently infer causality about the ways in which welfare receipt affects charitable activity. This approach to dealing with the problem of selection bias capitalizes on the known treatment-associated variance in the X matrix, transforming data to estimate unbiased treatment effects. We contribute to both the substantive and methodological literatures with this work.

To better understand who is served by child care subsidy systems and what services they receive, research is needed that examines the dynamics of subsidy use across multiple state policy contexts. Such research has been limited by the lack of comparable micro-data at the state level. Child Care Policy Research Partnerships funded by the U.S. Department of Health and Human Services have helped to fill this gap by constructing comparable, analyzable data sets in several states. This study made use of data sets constructed by three of the Child Care Research Partnerships. Consortium members representing Illinois, Maryland, Massachusetts, and Oregon joined together to build a collaborative, cross-state research design. Researchers in Texas, who were already engaged in similar research, agreed to join the project. Researchers from each of the states met together several times over a two-year period to develop comparable longitudinal data sets using administrative data from state child care subsidy systems. The research team included policy experts familiar with each of the five states and analysts familiar with administrative data and analytic methods. State agency partners played a critical role in helping the research partners understand data elements and policies in each state, and provided valuable feedback on the study results and interpretations. This study provides important new information about the characteristics of children and families who received subsidies, the services they received, the length of time they received services, and the stability of children’s care arrangements while in the subsidy system.