This paper establishes the consequences of a wrong specification on the quality of the data envelopment analysis. Specifically, the case of omitting a relevant variable in the input oriented problem is analyzed when there are different correlation structures between the inputs. It is established...

Selective attrition out of longitudinal datasets is a concern for empirical researchers. This paper discusses a simple way to identify both direction and magnitude of potential sample bias in household panels. The idea is to exploit multiple types of simultaneous entries into the panel. The...

This paper uses average monthly returns and linear spline regressions to investigate the relation between expected return and firm size during 1980-1994. We find that the average monthly returns are approximately constant across size deciles. The estimated spline regressions vary substantially...

In this paper we show that omitted variables and publication bias lead to severely biased estimates of the value of a statistical life. Although our empirical results are obtained in the context of a study of choices about road safety, we suspect that the same issues plague the estimation of...

In this paper we consider a weighted harmonic mean of two inconsistent estimators to propose a new estimator of the coefficient of a linear regression model with measurement errors. The proposed estimator is simple and it does not depend on any unknown quantity. The approximate bias and MSE of...