Job-Match Quality as an Error Component and the Wage-Tenure Profiler A Comparison and Test of Alternative Estimators
检验工作匹配假说，即标准工资方程中的误差项与任期相关导致任期效应被高估，使用豪斯曼方法得到一致估计，结果拒绝原假设但任期效应与匹配模型预期相反。
The job-matching hypothesis implies that the disturbance of the standard-wage equation is correlated with one of the regressors, tenure, causing an overestimation of the effect of tenure on wages. This hypothesis is tested and consistent estimates of wage-equation parameters obtained using the methods of Hausman (1978). The approach treats job-match quality as a component of the disturbance term, and an error-components estimator is compared to a modified fixed-effects estimator. The results reject the hypothesis of no correlation between the disturbance term and tenure, but the estimated value of the tenure effect is contrary to the matching model. Other models that may be consistent with these results are discussed.