Skip to main content
. Author manuscript; available in PMC: 2016 Mar 15.
Published in final edited form as: Rev Econ Stat. 2015 Dec 8;97(5):951–964. doi: 10.1162/REST_a_00535

Table 2.

Regression Estimates of Survival on DRG Inputs and the Effective Treatments Diffusion Factor

Dependent Variable One-Year Survival One-Year Survival
Diffusion Factor
(continuous)
0.014
(0.001)
Diffusion Quintile 2 0.009
(0.002)
Diffusion Quintile 3 0.016
(0.002)
Diffusion Quintile 4 0.024
(0.003)
Diffusion Quintile 5 0.027
(0.002)
Log
(DRG)
0.022
(0.004)
0.023
(0.004)
R2 0.09 0.09

Notes: Each column reports estimates from a separate regression in which an observation is a hospital-year, with N = 49,937 hospital-years. All regressions are weighted by the number of patients in each hospital-year. The dependent variable is the risk-adjusted one-year survival rate among AMI patients. The diffusion factor and quintiles are based on the common factor estimated from a 1-factor model of hospital use of aspirin, β blockers, and reperfusion. Log(DRG) is the log of the risk-adjusted total DRG weights per patient in the year following their AMI. Year dummy variables are included in all regressions. Risk-adjusted survival and DRG weights are derived from Medicare claims data from 1986–2004. The sample is limited to hospital/year observations with at least 5 observations per hospital. Standard errors (clustered at the hospital level) are in parentheses.