Lottery Expenditures in Canada: Regional Analysis of Probability of Purchase, Amount of Purchase, and Incidence.

This article has two purposes: First, to examine the effect of household characteristics on lottery expenditures in six regions of Canada using a double hurdle model to distinguish between the decision to play and the decision of how much to spend. In consumption studies, double hurdle models can be used to separate the decision to consume (participate) from the level of consumption (expenditures) and, therefore, provide more meaningful insights into consumers' behavior than does the Tobit model (Cragg, 1971). The second column, "Lottery Expenditures as a % of Household Income", reports total lottery expenditures as a percentage of after-tax household income for all households engaging in lottery expenditures. This means that the income elasticity of lottery expenditures at the mean is only 0.299, and an income elasticity of less than 1 denotes a regressive pattern of expenditures, which leads to a regressive tax. In general, lottery expenditures increase as household after-tax incomes increase, and lottery expenditures decline as the education level of the reference person increases. [Extracted from the article]