The Tiebout model, which theorizes that residential choice can regulate the supply of local collective goods, has generated much criticism, but few empirical tests of its behavioural assumptions. The article presents the findings of the first British micro-level test of the effect of local taxes and services on geographical mobility, a postal survey of households' moving decisions in four London boroughs during the years of the poll tax. Taxes and services are found to be important factors in the moving decision, corroborating the behavioural assumptions of the model. Respondents acted Tiebout-rationally as those moving into low tax/good service quality boroughs are more likely to cite low taxes and good services as a moving factor than those doing the reverse. The policy implications, however, remain contingent on political orientation.