Skip to main content

Table 3 Results for regression tests for publication bias

From: Meta-analysis of alcohol price and income elasticities – with corrections for publication bias

Alcohol beverage

Intercept (se)

Precision (se)

Beer prices

 (n = 172, R2 = 0.238)

−1.425 (.217)*

−0.172 (.045)*

Beer income

 (n = 151, R2 = 0.272)

1.266 (1.20)

0.405 (.183)*

Wine prices

 (n = 178, R2 = 0.230)

−2.057 (.509)*

−0.228 (.037)*

Wine income

 (n = 155, R2 = 0.176)

3.113 (.852)*

0.388 (.183)*

Spirits prices

 (n = 182, R2 = 0.353)

−1.530 (.450)*

−0.388 (.083)*

Spirits income

 (n = 160, R2 = 0.459)

2.299 (.640)*

0.657 (.141)*

Total alcohol prices

 (n = 105, R2 = 0.284)

−1.830 (.917)*

−0.316 (.135)*

Total alcohol income

 (n = 77, R2 = 0.419)

2.113 (.327)*

0.322 (.068)*

  1. Asterisks indicate the robust t-statistic is greater than 2.0 in absolute value. Robust standard errors (se) in parentheses obtained using cluster options in Stata 12, adjusted for seven country groups. Country-level groups are: (1) Australia and New Zealand; (2) Canada; (3) Europe (Belgium, Cyprus, Czech Republic, France, Germany, Greece, Hungary, Italy, Netherlands, Poland, Portugal, Romania, Spain, Multiple); (4) Nordic (Denmark, Finland, Norway, Sweden); (5) United Kingdom and Ireland; (6) United States; and (7) Other (Chile, China, India, Japan, Kenya, Russia, Taiwan, Tanzania, Turkey).
Back to article page