It is standard practice in applied work to rely on linear least squares regression to estimate the effect of a binary variable ("treatment") on some outcome of interest. In this paper I study the interpretation of the regression estimand when treatment effects are in fact heterogeneous.I show...

We analyse gender wage inequalities in Italy in the mid-1990s and in the mid-2000s. In this period important labour market developments occurred: institutional changes have loosened the use of flexible and atypical contracts; the female employment rates and educational levels have substantially...

This paper studies the gender wage gap by educational attainment in Italy using the 1994-2001 ECHP data. We estimate wage distributions in the presence of covariates and sample selection separately for highly and low educated men and women. Then, we decompose the gender wage gap across all the...

Sizeable gender differences in employment rates are observed in many countries. Sample selection into the workforce might therefore be a relevant issue when estimating gender wage gaps. This paper proposes a new semi-parametric estimator of densities in the presence of covariates which...

From the point of view of workplace safety, it is important to know whether having a temporary job has an effect on the severity of workplace accidents. We present an empirical analysis on the severity of workplace accidents by type of contract. We used micro data collected by the Italian...

In 2007 the Italian central government started a program by transferring funds to regional governments to develop both private and public early childcare services. Exploiting the different timing of program implementation across regions, we evaluate its effectiveness in boosting the public...

In this paper I develop a consistent estimator of the population average treatment effect (PATE) which is based on a nonstandard version of the Oaxaca–Blinder decomposition. As a result, I extend the recent literature which has utilized the treatment effects framework to reinterpret this...

Applied work often studies the effect of a binary variable ("treatment") using linear models with additive effects. I study the interpretation of the OLS estimands in such models when treatment effects are heterogeneous. I show that the treatment coefficient is a convex combination of two...

Currently there is little practical advice on which treatment effect estimator to use when trying to adjust for observable differences. A recent suggestion is to compare the performance of estimators in simulations that somehow mimic the empirical context. Two ways to run such 'empirical Monte...

In this paper we study doubly robust estimators of various average treatment effects under unconfoundedness. We unify and extend much of the recent literature by providing a very general identification result which covers binary and multi-valued treatments; unnormalized and normalized weighting;...