Skip to main content
. Author manuscript; available in PMC: 2014 Feb 26.
Published in final edited form as: Ann Appl Stat. 2012 Dec;7(3):1362–1385. doi: 10.1214/12-AOAS624

Table 2.

Fixed-effects panel regressions with state mortality modeled as a function of economic conditions for the 50 US states.

Basic model Linear state-specific trends

B1 B2 B3 B4 L1 L2 L3 L4
State unemployment -0.52*** (0.07) 0.12 (0.07) -0.67*** (0.09) -0.31*** (0.05) -0.41*** (0.04) -0.30*** (0.06)
National unemployment 0.78*** (0.08) 1.36*** (0.11) -0.46*** (0.05) -0.20** (0.07)
Year effects Yes No No No Yes No No No
AIC -5818.3 -5027.5 -5114.7 -5165.0 -7569.6 -6938.5 -6917.7 -6945.0

The model specifications are as described in equation (1) and Table 1, and were estimated using least squares, with states weighted by the square root of the state population. The state unemployment effect is reported as the estimate of 100α, the percentage increase in mortality due to a unit increase in unemployment. Similarly, the national unemployment effect is given as the estimate of 100β. Corresponding OLS standard errors (as used by Ruhm, 2000) are in parentheses.

***

P < 0.001,

**

P < 0.01,

*

P < 0.05,

P < 0.1.