Using linked housing and tax records from Denmark combined with a major reform of the mortgage interest deduction in the late 1980s, we carry out the first comprehensive long-term study of how tax subsidies affect housing decisions. The reform introduced a large reduction of the mortgage deduction for high-income taxpayers, a smaller reduction for middle-income tax- payers, and almost no change for lower-income taxpayers. We present four main findings. First, the mortgage deduction has a precisely estimated zero effect on homeownership for high- and middle-income households. Second, the mortgage deduction has a clear effect on housing de- mand at the intensive margin, inducing homeowners to buy larger and more expensive houses. Third, the deduction has sizeable effects on household financial decisions, inducing them to increase indebtedness. Finally, we provide suggestive evidence that the reduced tax subsidy to housing was capitalized into house prices.