Replication data for: Estimating Neighborhood Choice Models: Lessons from a Housing Assistance Experiment

  • Sebastian Galiani (Creator)
  • Alvin Murphy (Creator)
  • Juan Pantano (Creator)



We use data from a housing-assistance experiment to estimate a model of neighborhood choice. The experimental variation effectively randomizes the rents which households face and helps identify a key structural parameter. Access to two randomly selected treatment groups and a control group allows for out-of-sample validation of the model. We simulate the effects of changing the subsidy-use constraints implemented in the actual experiment. We find that restricting subsidies to even lower poverty neighborhoods would substantially reduce take-up and actually increase average exposure to poverty. Furthermore, adding restrictions based on neighborhood racial composition would not change average exposure to either race or poverty. (JEL I32, I38, R23, R38)
Date made available2015

Cite this