Skip to main content
. Author manuscript; available in PMC: 2018 Jul 16.
Published in final edited form as: Health Econ. 2014 Mar 10;24(5):566–582. doi: 10.1002/hec.3045

Table 2.

Calories from Soft Drinks: Ages 18–90

Linear Quadratic Cubic Quartic

Soft Drink Tax Rate 1.566 (2.447) 0.569 (5.866) −6.717 (11.575) −2.377 (15.066)
Soft Drink Tax Rate^2 0.102 (0.408) 2.347 (2.788) −0.293 (8.448)
Soft Drink Tax Rate^3 −0.149 (0.171) 0.290 (1.420)
Soft Drink Tax Rate^4 −0.022 (0.071)
Observations 35940 35940 35940 35940
F Statistic 0.410 0.062 0.399 0.275
P-Value 0.526 0.804 0.674 0.843
BIC 484050.8 484061.2 484070.6 484081.1

Notes: Each column represents a separate regression. Heteroskedasticity-robust standard errors that allow for clustering within states are in parentheses. The F statistic and corresponding p-value are based on the null hypothesis that the coefficient for the soft drink tax rate and all higher order polynomial terms are jointly equal to zero. Additional variables include female, age, age squared, black, other race, whether the food diary is from a weekday, state, year, and quarter. All regressions utilize NHANES survey weights.

Source: NHANES 1989 – 2006