Working Paper: NBER ID: w9812
Authors: Jonathan Meer; Harvey S. Rosen
Abstract: Most data sets indicate a positive correlation between having health insurance and utilizing health care services. Yet the direction of causality is not at all clear. If we ob-serve a positive correlation between the utilization of health care services and insurance status, we do not know if this is because people who anticipate poor health buy more in-surance (or take jobs with generous medical coverage), or because insurance lowers the cost of health care, increasing the quantity demanded. While a few attempts have been made to implement an instrumental variables (IV) strategy to deal with endogeneity, the instruments chosen have not been entirely convinc-ing. In this paper we revisit the IV estimation of the reduced form relationships between insurance and health care utilization taking advantage of what we argue is a good instru-ment - the individual's self-employment status. Our main finding is that a positive and statistically significant effect of insurance continues to obtain even after instrumenting. Indeed, instrumental variables estimates of the impact of insurance on utilization of a variety of health care services are larger than their non-instrumented counterparts. The validity of this exercise depends on the extent to which self-employment status is a suitable instrument. To argue this case, we analyze panel data on transitions from wage-earning into self-employment and show that individuals who select into self-employment do not differ systematically from those who remain wage-earners with re-spect to either the utilization of health care or health status. While this finding does not prove that self-employment status is an appropriate instrument, it is encouraging that there appear to be no underlying differences that might lead to self-employment per se affecting health services utilization.
Keywords: Health Insurance; Medical Services; Utilization; Instrumental Variables
JEL Codes: I1
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Health insurance (I13) | Utilization of medical services (I11) |
| Health insurance (I13) | Likelihood of visiting an office-based care provider (I11) |
| Health insurance (I13) | Likelihood of having a physical exam (I11) |
| Health insurance (I13) | Likelihood of having a mammogram (C52) |
| Health insurance (I13) | Various preventive procedures (I19) |
| Health insurance (I13) | Probability of overnight hospital stays (I11) |
| Health insurance (I13) | Probability of outpatient visits (I11) |
| Self-employment status (L26) | Health insurance (I13) |
| Self-employment status (L26) | Utilization of medical services (I11) |