Black-white wage differentials in a multiple sample selection bias model

This paper simultaneously incorporates two sources of selection bias in the black-white wage equations. It demonstrates that the biases due to an individual's propensity to be in the labor force and the firm's hiring practices are important in determining the black-white wage differential and failure to account for both biases will result in inaccurate estimation of the black-white wage differential. We found that adjusting for double selection bias in the wage equation, the black-white female wage gap is 26% larger than the black-white male wage gap, and 12.1% larger when we adjust for a single selection bias. The results seem to suggest that at the macro level, the enforcement of policies related to racial issues in the labor market will likely lead to a reduction in the black-white wage gap.