Table 1

Fixed effects regression estimates of the effect of smoke-free restaurant policies on restaurant business, 1992 to 1998

Model 1Model 2
All establishmentsAlcohol serving establishments
Dependent variableIn (per capita MEALS)In (per capita ALCMEALS)
Standard errors of coefficient estimates are in parentheses.
Unit of observation is the town/month.
Regression models were weighted using town level restaurant frequency and corrected for first order autocorrelation.
Income and meals data were adjusted for inflation using the Boston area consumer price index. Base month = December 1998.
*Significant at the <0.1 level; **significant at the <0.05 level; ***significant at the <0.01 level.
Sources: Center for Health Economics Research analysis of the Massachusetts Department of Revenue meals tax database, US Bureau of Economic Analysis county per capita income estimates, and US Bureau of the Census population estimates.
Independent variable0.0031***0.0041***
Time trend (TIME)(0.0002)(0.0005)
Highly restrictive restaurant policy0.00020.0021
post-adoption time trend (TIMEH)(0.0007)(0.0017)
Other restaurant policy0.0004−0.0005
post-adoption time trend (TIMEO)(0.0003)(0.0007)
Second quarter (QTR2)0.1704***0.1403***
(0.0039)(0.0071)
Third quarter (QTR3)0.2015***0.1499 ***
(0.0045)(0.0082)
Fourth quarter (QTR4)0.0902***0.0478***
(0.0040)(0.0074)
ln county per capita income (INCOME)0.1831***0.1258 ***
(0.0295)(0.0537)
Percent border towns with smoke-free policies (BORDER)0.0785***0.0151
(0.0295)(0.0674)
n198376557
R2 (F) without town dummies0.10 (268.36)0.20 (204.22)
R2 (F) with town dummies0.92 (983.72)0.85 (441.34)