作者: Joseph J. Capuno , Carlos Antonio R. Tan
DOI:
关键词: Pediatrics 、 Causal model 、 Probit model 、 Diarrhea 、 Incidence (epidemiology) 、 Child health 、 Percentage point 、 Medicine 、 Environmental health 、 Observational study 、 Water treatment
摘要: The treatment of drinking water is advocated to reduce the incidence child diarrhea. However, evaluating impact with only observational data leads biased estimates since it could be occurrence diarrhea that induced household treat their water. To deal possible simultaneity between and diarrhea, we specify non-recursive two-equation causal models apply on a sub-sample households children below five years old from Philippine National Demographic Health Surveys. In effects model, find reduces by 5.2 percentage points proportion under-5 afflicted instrumental-variable probit have higher propensity sterilize 1.2 given one point increase in Ignoring yields misleading result increases These results underscore need insure quality at use not just source.