This article assesses the impact of the Children’s Health Insurance Program (CHIP) on health insurance coverage distribution among low-income children. Data for this analysis come from the National Survey of America’s Families (NSAF) from 1997, 1999 and 2002. This nationally representative household survey oversamples low-incomes families, sampling a total of 62,497 children across all three years. This quasi-experimental study tests the sensitivity of the results by using two different approaches: difference-in-differences (DD) approach and an instrumental variables (IV) approach. The DD approach allows for estimation of separate impacts for those already eligible for CHIP and those made eligible. The IV approach addresses issues of endogeneity and measurement error.
The authors conclude that the CHIP program and its implementation resulted in large increases in public coverage. Reductions in uninsurance were made without causing substantial employer-coverage erosion. Additionally, their analysis suggests estimates that are similar to Congressional Budget Office projections of crowd-out.