Search Results
Report
Mixture of normals probit models
This paper generalizes the normal probit model of dichotomous choice by introducing mixtures of normals distributions for the disturbance term. By mixing on both the mean and variance parameters and by increasing the number of distributions in the mixture these models effectively remove the normality assumption and are much closer to semiparametric models. When a Bayesian approach is taken, there is an exact finite-sample distribution theory for the choice probability conditional on the covariates. The paper uses artificial data to show how posterior odds ratios can discriminate between ...
Report
The solution and estimation of discrete choice dynamic programming models by simulation and interpolation: Monte Carlo evidence
Over the past decade, a substantial literature on the estimation of discrete choice dynamic programming (DC-DP) models of behavior has developed. However, this literature now faces major computational barriers. Specifically, in order to solve the dynamic programming (DP) problems that generate agents' decision rules in DC-DP models, high dimensional integrations must be performed at each point in the state space of the DP problem. In this paper we explore the performance of approximate solutions to DP problems. Our approximation method consists of: 1) using Monte Carlo integration to simulate ...
Discussion Paper
The employment and wage effects of oil price shocks: a sectoral analysis
In this paper we use micro panel data to examine the effects of oil price shocks on employment and real wages, at the aggregate and industry levels. We also measure differences in the employment and wage responses for workers differentiated on the basis of skill level. We find that oil price increases result in a substantial decline in real wages for all workers, but raise the relative wage of skilled workers. The use of panel data econometric techniques to control for unobserved heterogeneity is essential to uncover this result, which is completely hidden in OLS estimates. While the ...
Report
Statistical inference in the multinomial multiperiod probit model
Statistical inference in multinomial multiperiod probit models has been hindered in the past by the high dimensional numerical integrations necessary to form the likelihood functions, posterior distributions, or moment conditions in these models. We describe three alternative approaches to inference that circumvent the integration problem: Bayesian inference using Gibbs sampling and data augmentation to compute posterior moments, simulated maximum likelihood (SML) estimation using the GHK recursive probability simulator, and method of simulated moment (MSM) estimation using the GHK simulator. ...
Working Paper
Health Shocks, Health Insurance, Human Capital, and the Dynamics of Earnings and Health
We specify and calibrate a life-cycle model of labor supply and savings incorporating health shocks and medical treatment decisions. Our model features endogenous wage formation via human capital accumulation, employer-sponsored health insurance, and means-tested social insurance. We use the model to study the effects of health shocks on health, labor supply and earnings, and to assess how health shocks contribute to earnings inequality. We also simulate provision of public insurance to agents who lack employer-sponsored insurance. The public insurance program substantially increases medical ...
Discussion Paper
Nominal contracting theories of unemployment: evidence from panel data
This paper examines the response of real wages and employment probabilities to nominal shocks using micro-panel data from the National Longitudinal Survey of Young Men. Both economy-wide and sector-specific responses to nominal shocks are examined. The observed response patterns are inconsistent with nominal contract based theories of unemployment. These theories predict that nominal surprises should be negatively correlated with real wages in sectors with nominal contracting. In fact, inflation surprises are found to be essentially uncorrelated with real wages in all sectors, while money ...
Discussion Paper
The relation between skill levels and the cyclical variability of employment, hours and wages
This paper uses micro data to examine differences in the cyclical variability of employment, hours, and wages for skilled and unskilled workers. Contrary to conventional wisdom, we find that, at the aggregate level, skilled and unskilled workers are subject to essentially the same degree of cyclical variation in wages. That is, relative offer wage differentials between skilled and unskilled workers are acyclical. However, we do find important differences in the patterns of employment and hours variation for skilled vs. unskilled workers when a college degree is used as a proxy for skill. ...
Discussion Paper
Sectoral shift theories of unemployment: evidence from panel data
This paper examines the response of sectoral real wages and location probabilities to oil price shocks using U.S. micro-panel data (the National Longitudinal Survey of Young Men). The goal is to determine whether the observed response patterns are consistent with so-called sectoral shift theories of unemployment. These theories predict that shocks that change sectoral relative wages should increase unemployment in the short run and lead to labor reallocation in the long run. Consistent with these predictions, the oil price changes of the 1970s resulted in substantial movements in industry ...
Working Paper
Robust Inference for the Frisch Labor Supply Elasticity
The Frisch labor supply elasticity plays a key role in many economic policy debates, but its magnitude remains controversial. Many studies estimate the Frisch elasticity using 2SLS regressions of hours changes on wage changes. But a little appreciated power asymmetry property of 2SLS causes estimates to appear spuriously imprecise when they are shifted away from the OLS bias. This makes it difficult for a 2SLS t-test to detect a true positive Frisch elasticity. We illustrate this problem in an application to NLSY97 data. We obtain an estimate of 0.60 for young men, but the t-test indicates it ...