Households hold undiversified stock portfolios of firms headquartered near their city of residence. Leading explanations assign a causal role for proximity. The literature neglects that distance is endogenous. Households may locate based on unobservables such as optimism about a city’s economic prospects, which can be correlated with latent local-stock demand. We use location-choice models to account for this selection. We propose as instruments that older households prefer to locate in recreational areas for non-pecuniary reasons. Our analysis based on a widely used household data set yields significantly smaller estimates for proximity in determining portfolio choice compared to those in the literature.