Now showing 1 - 3 of 3
ItemGambling with Stimulus Payments: Feeding Gaming Machines with Federal DollarsHirschberg, JG ; Lye, JN (Department of Economics, The University of Melbourne, 2013)In late 2008 and early 2009 the Australian Federal Government introduced a series of economic stimulus packages designed to maintain consumer spending in the early days of the Great Recession. When these packages were initiated the media suggested that the wide-spread availability of electronic gaming machines (EGMs, eg. slot machines, poker machines, video lottery terminals) in Australia would result in stimulating the EGMs. Using state level monthly data we estimate the degree to which the stimulus payments influenced EGM expenditure and the implications for state and territory gaming tax revenues.
ItemConfidence Intervals for Ratios: Econometric Examples with StataLye, JN ; Hirschberg, JG ( 2018)Ratios of parameter estimates are often used in econometric applications. However, the test of these ratios when estimated can cause difficulties since the ratio of asymptotically normally distributed random variables have a Cauchy distribution for which there are no finite moments. This paper presents a method for the estimation of confidence intervals based on the Fieller approach that has been shown to be preferable to the usual Delta method. Using example applications in both Stata and R, we demonstrate that a few extra steps in the examination of the estimate of the ratio may provide a confidence interval with superior coverage.
ItemTell Me Something I Don’t Already Know: Informedness and External Validity in Information ProgramsBYRNE, D ; La Nauze, A ; Martin, LA (Department of Economics, University of Melbourne, 2014)Information programs that leverage peer comparisons are used to encourage pro-social behavior in many contexts. We document how imperfect information generates heterogenous responses to treatments involving personalized feedback and peer comparisons. In our field experiment in retail electricity, we find that most households either overestimate or underestimate their relative energy consumption pre-treatment. Households that overestimated respond to new information by temporarily increasing electricity consumption, whereas households that underestimated take steps that lead to long term energy conservation. We explore the implications of these results for the external validity and design of information programs.