Thomas J. Kniesner

Compensating wage differentials for fatal injury risk in Australia, Japan, and the United States

Our research infers the effects of institutionalized wage setting and lengthy worker-firm attachment by comparing estimated compensating wage differentials for fatal injury risk in Japanese, Australian, and U.S. manufacturing. Hedonic labor market equilibrium regressions for Japan reveal a statistically fragile compensating wage differential of 0% to 1.4% for exposure to the average fatality risk compared to employment in a perfectly safe workplace. Australian workers receive a statistically robust 2.5% estimated wage premium. Using new data on work-related fatalities, we find a 1% compensating wage differential in U.S. manufacturing that becomes more positive and statistically less significant as data are aggregated.

Estimating Life Cycle Labor Supply Tax Effects

We present an econometrically tractable life cycle labor supply model for panel data including intertemporally progressive taxes on uncertai wage and nonwge incomes. Our two‐stage fixedeffects generalized method‐of‐moments approach first extimates intretemporal and then intertemporal preferences. Specification testing domonstrates the value of incorporating joint progressive taxation of labor and nonlabor incomes, Results for prime‐age men emphasize the roles played by hourly wage endogeneity, worker‐specific effects, the measure of the rate of pay, and intemporal budget constaint, nonseparability, Simulations indicate that recent tax reform, while not self‐financing, stimulated made labor supplied by about 3 percent and reduced deadweight loss about 16 percent.

On the Measurement of Job Risk in Hedonic Wage Models

We examine the incidence, form, and research consequences of measurement error in measures of fatal injury risk in U.S. workplaces using both Bureau of Labor Statistics and National Intitute of Occupational Safety and Health data. Of the various measures examined the NIOSH industry risk measure produces implicit value of life estimates most in line with both economic theory and the mode result for the existing literature. Because we find non-classical measurement error that differs across risk measures and is not independent of other regressors, innovative statistical procedures need be applied to obtain statistically improved estimates of wage-fatality risk tradeoffs.

The Value of a Statistical Life: Evidence from Panel Data

Our research addresses fundamental long-standing concerns in the compensating wage differentials literature and its public policy implications: the econometric properties of estimates of the value of statistical life (VSL) and the wide range of such estimates from about

The Importance of Sample Attrition in Life Cycle Labor Supply Estimation

0 to almost

Count Data Models with Variance of Unknown Form: An Application to a Hedonic Model of Worker Absenteeism

30 million. Here we address most of the prominent econometric issues by applying panel data, a new and more accurate fatality risk measure, and systematic application of panel data estimators. Controlling for measurement error, endogeneity, latent individual heterogeneity that may be correlated with the regressors, state dependence, and sample composition yields an estimated value of a statistical life of about

Value of a Statistical Life: Relative Position vs. Relative Age

7 million–

Effect of mental health specialty care on antidepressant length of therapy.

12 million, which we show can clarify greatly the cost-effectiveness of regulatory decisions. We show that probably the most important econometric issue is controlling for latent heterogeneity; less important is how one does it.

Dealing with the common econometric problems of count data with excess zeros, endogenous treatment effects, and attrition bias

We examine the importance of possible nonrandom attrition to an econometric model of life cycle labor supply using both a Wald test comparing attriters to nonattriters and variable addition tests based on formal models of attrition. Estimates using the Panel Study of Income Dynamics show that nonrandom attrition is of little concern when estimating prime-age male labor supply because the effect of attrition is absorbed into fixed effects in labor supply. The wage measure and instrument set have much larger effects on the estimated labor supply function of prime-age men than how one adjusts for panel attrition.

The Full-Time Workweek in the United States, 1900-1970.

We examine an econometric model of counts of worker absences due to illness in a sluggishly adjusting hedonic labor market. We compare three estimators that parameterize the conditional varianceleast squares, Poisson, and negative binomial pseudo maximum likelihoodto generalized least squares (GLS) using nonparametric estimates of the conditional variance. Our data support the hedonic absenteeism model. Semiparametric GLS coefficients are similar in sign, magnitude, and statistical significance to coefficients where the mean and variance of the errors are specified ex ante. In our data, coefficient estimates are sensitive to a regressor list but not to the econometric technique, including correcting for possible heteroskedasticity of unknown form.