| Popis: |
Estimates of the value-of-life have relied heavily on labor market studies of compensating wages. These studies typically involve least squares regressions using cross-sectional data. The dependent variable is log of wages and the independent variables are years of schooling, age, age squared, and so on. The key independent variable is a measure of the death rate on the job. Most studies have found a strong partial correlation between log-wages and the death rate and most authors have interpreted this correlation as evidence that the labor market is generating compensating wages for hazardous work. Some economists have used the coefficient from this correlation to estimate a statistical value-of-life. I n t h i s p a p e r , w e f i r s t m e n t i o n s o m e e v i d e n c e t h a t c o r r e l a t i o n s b e t w e e n wages and death rates are fragile. We then discuss a study (Leigh, 1991) that did not find strong wage-death rate correlations using unique data on occupations. Third, we argue that the correlations found in prior literature are more likely the result of historical inter-industry differentials than the result of a compensating wage paid for dangerous work. The fourth part of the paper offers some explanations for why compensating wages fail to appear for the lion's share of jobs in the labor market but do appear for the handful of jobs that are undeniably hazardous. We offer a comment on the academic importance of forensic economists in the fifth part of the paper. A summary concludes our paper. I. Fragile Estimates Ted Miller (1990) reviewed 27 studies and Kip Viscusi (1992) reviewed 30 studies on compensating wages for job-related deaths, most of which found positive and statistically significant estimated coefficients on death rate variables. Virtually all of Miller’s studies were on Viscusi’s list. However, in several of these studies, the estimated coefficients for the death rate variables were either statistically insignificant or significant but close to zero (Dickens, 1984; Dorsey, 1983; Leigh and Folsom, 1984; Leigh, 1987; Moore and Viscusi, 1988; Thaler and Rosen, 1975; Viscusi, 1979; Kniesner and Leeth, 1991). More importantly, these two reviews are incomplete since they do not include at least two prior studies or three subsequent studies that failed to find statisti |
