A5007891245- Advanced Causal Inference Techniques
- School Choice and Performance
- Statistical Methods and Bayesian Inference
- Evaluation and Performance Assessment
- Employment and Welfare Studies
- Labor market dynamics and wage inequality
- Early Childhood Education and Development
- Statistical Methods and Inference
- Retirement, Disability, and Employment
- Education Systems and Policy
- Healthcare Policy and Management
- Gender, Labor, and Family Dynamics
- Labor Movements and Unions
- Urban, Neighborhood, and Segregation Studies
- Global trade and economics
- Health Systems, Economic Evaluations, Quality of Life
- Higher Education Research Studies
- Child and Adolescent Psychosocial and Emotional Development
- Education and Technology Integration
- Educational Assessment and Improvement
- Poverty, Education, and Child Welfare
- Family and Disability Support Research
- Statistical Methods in Clinical Trials
- Educational and Psychological Assessments
- Food Security and Health in Diverse Populations
Mathematica Policy Research
2013-2024
Families USA
2001
Columbia University
2001
Center for Children
2001
United States Department of Health and Human Services
2001
The University of Texas Southwestern Medical Center
2000
Southwestern Medical Center
2000
Early Head Start, a federal program begun in 1995 for low-income pregnant women and families with infants toddlers, was evaluated through randomized trial of 3,001 17 programs. Interviews primary caregivers, child assessments, observations parent-child interactions were completed when children 3 years old. Caregivers diverse race-ethnicity, language, other characteristics. Regression-adjusted impact analyses showed that 3-year-old performed better than did control cognitive language...
This paper presents findings from an experimental evaluation of Job Corps, the nation's largest training program for disadvantaged youths. The study uses survey data collected over four years and tax nine on a nationwide sample 15,400 treatments controls. Corps model has promise; participation increases educational attainment, reduces criminal activity, earnings several postprogram years. Based data, however, gains were not sustained except oldest participants. Nonetheless, is only federal...
This article examines theoretical and empirical issues related to the statistical power of impact estimates for experimental evaluations education programs. The author considers designs where random assignment is conducted at school, classroom, or student level, employs a unified analytic framework using methods from literature. Focusing on standardized test scores elementary school students, this discusses appropriate precision standards and, each design, required number schools achieve...
This article examines theoretical and empirical issues related to the statistical power of impact estimates under clustered regression discontinuity (RD) designs. The theory is grounded in causal inference hierarchical linear modeling literature, work focuses on common designs used education research test intervention effects student scores. main conclusion that three four times larger samples are typically required RD than experimental produce impacts with same level precision. Thus,...
Abstract The objective of the Registry was to characterize population infants receiving prophylaxis for respiratory syncytial virus (RSV) disease by describing patterns and scope usage palivizumab in a cross section US infants. RSV hospitalization outcomes were also described. Palivizumab (Synagis®, MedImmune, Inc., 25 West Watkins Mill Road, Gaithersburg, MD 20878) Outcomes prospective multicenter survey conducted at 63 sites. Demographics, injection history, collected on 2,116 palivizumab....
Early Head Start, a federal program begun in 1995 for low-income pregnant women and families with infants toddlers, was evaluated through randomized trial of 3,001 17 programs. Interviews primary caregivers, child assessments, observations parent-child interactions were completed when children 3 years old. Caregivers diverse race-ethnicity, language, other characteristics. Regression-adjusted impact analyses showed that 3-year-old performed better than did control cognitive language...
In social policy evaluations, the multiple testing problem occurs due to many hypothesis tests that are typically conducted across outcomes and subgroups, which can lead spurious impact findings. This article discusses a framework for addressing this balances Types I II errors. The involves specifying confirmatory exploratory analyses in study protocols, delineating outcome domains, conducting t on composite domain outcomes, applying multiplicity corrections composites domains obtain...
This article addresses likely error rates for measuring teacher and school performance in the upper elementary grades using value-added models applied to student test score gain data. Using a realistic measurement system scheme based on hypothesis testing, authors develop rate formulas ordinary least squares Empirical Bayes estimators. results suggest that estimates are be noisy amount of data typically used practice. Type I II comparing teacher’s average about 25% with 3 years 35% 1 year...
This article examines the estimation of two-stage clustered designs for education randomized control trials (RCTs) using nonparametric Neyman causal inference framework that underlies experiments. The key distinction between considered models is whether potential treatment and group outcomes are to be fixed study population (the finite-population model) or randomly selected from a vaguely defined universe super-population model). Both approaches allow heterogeneity effects. Appropriate...
In randomized control trials (RCTs) in the education field, complier average causal effect (CACE) parameter is often of policy interest, because it pertains to intervention effects for students who receive a meaningful dose treatment services. This article uses inference and instrumental variables framework examine identification estimation CACE two-level clustered RCTs. The also provides simple asymptotic variance formulas impact estimators measured nominal standard deviation units....
This article discusses the use of propensity scoring in experimental program evaluations to estimate impacts for subgroups defined by features and participants' experiences. The authors discuss estimation issues provide specification tests. They also an overlooked data collection design--obtaining predictions that intake staff make about applicants' likely assignments experiences--that could improve quality matched comparison samples. demonstrate effectiveness this approach producing...
This article develops design-based ratio estimators for clustered, blocked randomized controlled trials (RCTs), with an application to a federally funded, school-based RCT testing the effects of behavioral health interventions. We consider finite population weighted least-square average treatment (ATEs), allowing general weighting schemes and covariates. models block-by-treatment status interactions as well restricted block indicators only. prove new central limit theorems each...