We evaluate the effect of the size of deductibles in the basic health insurance in Switzerland on the probability of a doctor visit. We employ nonparametric bounding techniques to minimise statistical assumptions. In order to tighten the bounds we consider two further assumptions: mean independence of an instrument and monotone treatment response. Under these two assumption we are able to bound the causal effect of high deductibles compared to low deductibles below zero. We conclude that the difference in health care utilisation is partly due to a reduction of moral hazard effects.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1002/hec.1113 | DOI Listing |
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!