The Influence of Current and Past Alcohol Use on Earnings: Three Approaches to Estimation
This article examines alcohol consumption and wages of males, aged 21 through 28, from three different perspectives. First, a four-equation model employs the National Longitudinal Survey of Youth to estimate a wage equation and an hours-of-work-equation for heavy drinkers and contrasts these estimates with wage and hours equations for moderate drinkers. Using a variety of drinking thresholds to distinguish "heavy" drinkers from "moderate" ones, the association between current levels of drinking, wages, and hours of work is measured. The longitudinal nature of the data is then used to study the relation between a profile of drinking over the 1982-1985 period and earnings. Last, a wage-change model investigates how the profile of drinking over the period 1982-1984 is related to the wage change between 1982 and 1985. The results from the static single-period model differ markedly from the wage-change model. Cross-sectional data show that higher drinking levels are correlated with higher wages and hours of work. Over time, however, increased drinking is associated with lower wages.
R. R. Bryant et al., "The Influence of Current and Past Alcohol Use on Earnings: Three Approaches to Estimation," Journal of Applied Behavioral Science, SAGE Publications, Jan 1993.
The definitive version is available at http://dx.doi.org/10.1177/0021886393291002
Mathematics and Statistics
Article - Journal
© 1993 SAGE Publications, All rights reserved.