I estimate the effect of immigration on wages of native male workers correcting for endogenous allocation of immigrants across education–experience cells. Exogenous variation is obtained from interactions of push factors, distance, and skill-cell dummies: distance mitigates the effect of push factors more severely for some skill groups. I propose a two-stage approach (Subsample 2SLS) that estimates the first stage regression with an augmented sample of destination countries and the second stage with a restricted subsample of interest. Asymptotic properties are discussed. Results show important OLS biases. For the United States and Canada, Subsample 2SLS elasticities average around minus one, very stable across alternative specifications and different instruments.