Working Paper: NBER ID: w28817
Authors: Seth Richards-Shubik; Mark S. Roberts; Julie M. Donohue
Abstract: Unlike demand studies in other industries, models of provider demand in health care often must omit a price or any other factor that equilibrates the market. Estimates of the consumer response to quality may consequently be attenuated, if the limited capacity of individual providers prevents some consumers from obtaining higher quality. We propose a tractable method to address this problem by adding a congestion effect to standard discrete-choice models. We show analytically how this improves forecasts of the consumer response to quality. We then apply this method to the market for heart surgery, and find that the attenuation bias in estimated quality effects can be important empirically.
Keywords: No keywords provided
JEL Codes: C31; I11; L15
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| omission of price or equilibrating factor (D41) | biased estimates of the effect of quality on demand (L15) |
| congestion effect (L91) | attenuation bias in estimating consumer response to quality (L15) |
| increasing patient numbers (I11) | longer wait times (C41) |
| longer wait times (C41) | affecting perceived quality and demand (L15) |
| distances between patients and providers (I11) | capturing endogenous nature of market share (D16) |
| investment in provider quality (J24) | underestimated economic returns (J17) |
| provider quality (I11) | modest response among patients with more comorbidities (I12) |
| congestion effects in discrete-choice models (C25) | more accurate representation of market dynamics (D40) |