Water for Life: The Impact of the Privatization of Water Services on Child Mortality
read more
Citations
Closing the gap in a generation: health equity through action on the social determinants of health
Multivariate and Propensity Score Matching Software with Automated Balance Optimization: The Matching Package for R
Multivariate and Propensity Score Matching Software with Automated Balance Optimization: The Matching package for R
Genetic Matching for Estimating Causal Effects: A General Multivariate Matching Method for Achieving Balance in Observational Studies
Impact Evaluation in Practice
References
The central role of the propensity score in observational studies for causal effects
How Much Should We Trust Differences-In-Differences Estimates?
Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training Programme
Matching As An Econometric Evaluation Estimator
The Economics and Econometrics of Active Labor Market Programs
Related Papers (5)
The central role of the propensity score in observational studies for causal effects
Worms: Identifying Impacts on Education and Health in the Presence of Treatment Externalities
Frequently Asked Questions (9)
Q2. Why do the authors focus on young children?
The authors focus on young children because they are particularly vulnerable to water-related diseases due to weak body defenses, higher susceptibility, and greater exposure from inadequate knowledge of how to avoid risks; and because water related diseases can easily be prevented through access to clean drinking water, better hygiene and better sanitation (WHO, 2000).
Q3. What is the effect of privatization on child mortality in argentina?
In fact, the privatization of water systems is associated with a 26.5 percent reduction in child mortality in municipalities with high levels of poverty (UBN greater than 50%).
Q4. How does the method eliminate the bias due to different distributions of x?
Using observations in the treatment and control groups over the region of common support in the distribution of x eliminates the first source of concern, while the bias due to different distributions of x between treated and untreated municipalities within this common support is eliminated by reweighting the control group observations.
Q5. How does the model estimate the impact of privatization on child mortality?
the authors find that privatization is associated with a significant reduction in the child mortality rate of about 5 percent using the full sample regardless of the choice of controls.
Q6. What is the likely explanation for the increase in connections to the water network?
And Artana et al (2000) reports that after privatization in Corrientes, one of the poorest provinces in the country, the number of connections to the water network in the province rose by 22 percent and the number of sewerage connections increased by 50 percent.
Q7. How do the authors obtain the generalized difference-in-differences matching estimator?
the authors use a kernel density weighting procedure to obtain the generalized difference-in-differences matching estimator (see Heckman et al, 1997).
Q8. How does Rosenbaum and Rubin compare treated and untreated units?
Rosenbaum and Rubin (1983) show that to match treated and untreated units on the basis of x is equivalent to match them using a balancing score B(x).
Q9. What is the main source of bias in the estimation of mortality?
This is consistent with the results in Heckman et al (1998a) where they evaluated matching estimates using data from a controlled randomized experiment and found that the main source of bias comes from not restricting the estimates to the observations on the common support.