This paper contributes to the literature on temporary migration by developing a model of repeated circular migration that accounts for saving behavior. Using Mexican Migrant Project data on undocumented migrants and non-migrants, I estimate the parameters of the model through the Method of Simulated Moments. The intensity of U.S. border enforcement is found to have a significant positive effect on the cost of migration for at least one group of individuals. Counterfactual experiments suggest that an increase in the intensity of border enforcement over the sample period would have reduced migration rates in the sample, but would have increased trip durations. I do not find evidence for the hypothesis that tougher border enforcement increases the population of undocumented migrants by trapping them in the United States. Counterfactual simulations suggest that continual increases in border enforcement will not produce continual reductions in migration rates because some individuals are immune to the effects of such policy changes. Migration behavior is also found to be sensitive to changes in the exchange rate, which alter both the cost of migration and the value of foreign earnings.