What would be the counterfactual wage of civil servants if they were employed in theprivate sector? Using the French European Household panel, we present a newapproach to the wage differential between the public and the private sectors. Weestimate a model, which controls both for selection into employment, and for selfselectioninto the public sector. We also introduce unobserved heterogeneity in thepropensity to be employed in either job sector, and in the sector-specific productivity.Evidence based on the counterfactual distributions suggests a large public-privatewage premium for low public wages. This conclusion also holds for women but may beexplained by a weaker discrimination in the public sector. Unlike women, most malecivil servants would earn more in the private sector.