This paper shows that average wage gap decompositions between any two groups of workers can be carried out using nonparametric wage structures. It also proposes an algorithm to correct for sample selection in nonparametric models known as tree structures. This paper studies the wage gap between third-generation Mexican American and non-Hispanic white workers in the southwest. It is shown that the decomposition heavily depends on functional assumptions, and that different aproaches to flexibility may render sufficiently good and similar results