Specification and estimation of the price responsiveness of alcohol demand: a policy analytic perspective

dc.contributor.advisorTezra, Joseph V.
dc.contributor.authorDevaraj, Srikant
dc.contributor.otherAntwi, Yaa Akosa
dc.contributor.otherJones, Josette
dc.contributor.otherWu, Jisong
dc.date.accessioned2016-03-16T17:30:15Z
dc.date.available2016-03-16T17:30:15Z
dc.date.issued2016-01-13
dc.degree.date2016en_US
dc.degree.disciplineDepartment of Economics
dc.degree.grantorIndiana Universityen_US
dc.degree.levelPh.D.en_US
dc.descriptionIndiana University-Purdue University Indianapolis (IUPUI)en_US
dc.description.abstractAccurate estimation of alcohol price elasticity is important for policy analysis – e.g.., determining optimal taxes and projecting revenues generated from proposed tax changes. Several approaches to specifying and estimating the price elasticity of demand for alcohol can be found in the literature. There are two keys to policy-relevant specification and estimation of alcohol price elasticity. First, the underlying demand model should take account of alcohol consumption decisions at the extensive margin – i.e., individuals' decisions to drink or not – because the price of alcohol may impact the drinking initiation decision and one's decision to drink is likely to be structurally different from how much they drink if they decide to do so (the intensive margin). Secondly, the modeling of alcohol demand elasticity should yield both theoretical and empirical results that are causally interpretable. The elasticity estimates obtained from the existing two-part model takes into account the extensive margin, but are not causally interpretable. The elasticity estimates obtained using aggregate-level models, however, are causally interpretable, but do not explicitly take into account the extensive margin. There currently exists no specification and estimation method for alcohol price elasticity that both accommodates the extensive margin and is causally interpretable. I explore additional sources of bias in the extant approaches to elasticity specification and estimation: 1) the use of logged (vs. nominal) alcohol prices; and 2) implementation of unnecessarily restrictive assumptions underlying the conventional two-part model. I propose a new approach to elasticity specification and estimation that covers the two key requirements for policy relevance and remedies all such biases. I find evidence of substantial divergence between the new and extant methods using both simulated and the real data. Such differences are profound when placed in the context of alcohol tax revenue generation.en_US
dc.identifier.doi10.7912/C2T591
dc.identifier.urihttps://hdl.handle.net/1805/8884
dc.identifier.urihttp://dx.doi.org/10.7912/C2/569
dc.language.isoen_USen_US
dc.subjectAlcohol demanden_US
dc.subjectPrice elasticityen_US
dc.subjectTwo-part modelen_US
dc.subject.lcshAlcoholic beverages -- Prices -- Research -- Methodologyen_US
dc.subject.lcshElasticity (Economics) -- Measurementen_US
dc.subject.lcshAlcoholic beverage industry -- Econometric modelsen_US
dc.subject.lcshBeer -- Prices --Research -- Methodologyen_US
dc.subject.lcshConsumption (Economics) -- Econometric modelsen_US
dc.subject.lcshDemand (Economic theory) -- Econometric modelsen_US
dc.subject.lcshTax collectionen_US
dc.titleSpecification and estimation of the price responsiveness of alcohol demand: a policy analytic perspectiveen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Devaraj_iupui_0104D_10069.pdf
Size:
1.06 MB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.88 KB
Format:
Item-specific license agreed upon to submission
Description: