Skip to main content
. Author manuscript; available in PMC: 2013 May 2.
Published in final edited form as: Health Econ. 2011 Dec 12;22(1):89–105. doi: 10.1002/hec.1817

Table III.

Heterogeneity in price elasticity of alcohol demand

Negative binomial FMM component 1 FMM component 2 FMM prior probability of component 1 Test of difference between components—p-value
Log alcohol price −0.402***
(0.152)
−1.686***
(0.651)
0.0131
(0.0863)
0.0123
Age 61–70 −0.249***
(0.0299)
0.0551
(0.0981)
−0.164***
(0.0392)
0.178***
(0.0573)
0.0229
Age 71–80 −0.586***
(0.0462)
0.149
(0.130)
−0.467***
(0.0495)
0.356***
(0.102)
0.000
Age 81+ −1.039***
(0.0432)
−0.289
(0.179)
−0.939***
(0.0737)
0.310**
(0.135)
0.0002
Height 0.168
(0.308)
0.720
(0.510)
0.233
(0.242)
−0.0146
(0.483)
0.3081
Years of education 0.0432***
(0.00644)
0.250***
(0.0315)
−0.0672***
(0.00630)
−0.124***
(0.0156)
0.000
Black −0.351***
(0.0564)
−2.367***
(0.638)
−0.121*
(0.0688)
0.183
(0.125)
0.0002
Other race −0.227***
(0.0847)
−4.782
(11.06)
−0.0100
(0.135)
0.166
(0.220)
0.6631
Male 0.902***
(0.0627)
−0.00306
(0.127)
0.448***
(0.0361)
−0.850***
(0.0828)
0.0010
Constant −0.618
(0.608)
−2.407
(2.036)
0.802**
(0.404)
2.739***
(0.720)
Observations 65,002 65,002 65,002 65,002
Mean predicted y 0.13 1.86
Mean posterior probability 0.728 0.272

Regressions also include census region of residence and year dummies.

Standard errors in parentheses; regressions are weighted, and robust standard errors are clustered at the state level.

*

p<0.1

**

p<0.05

***

p<0.01.