This article examines the determinants of Canadian household expenditures on alcoholic beverages using double‐hurdle models to distinguish between the decision to consume and the decision of how much to consume. Linearity of the alcohol expenditurefunction and thus the applicability of a normality assumption to its errors is examined using Box‐Cox and inverse hyperbolic sine (IHS) transformations. As important policy decisions affecting alcohol usage cannot be regarded as being independent of those affecting tobacco expenditure, tobacco expenditures are considered here as an important determinant of alcohol usage. Results of Hausman tests and two‐step instrumental variables estimation to examine the possibility of simultaneity between household expenditure on alcohol and tobacco are also discussed.
No takes yet. Share an insight, caveat, or question.
Abdel-Ghany et al. (1998) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: