We test the interest rate sensitivity of subprime credit card borrowers using a unique panel data set from a UK credit card company. What is novel about our contribution is that we were given details of a randomized interest rate experiment conducted by the lender between October 2006 and January 2007. We find that individuals who tend to utilize their credit limits fully do not reduce their demand for credit when subject to increases in interest rates as high as 3 percentage points. This finding is naturally interpreted as evidence of binding liquidity constraints. We also demonstrate the importance of truly exogenous variation in interest rates when estimating credit demand elasticities. We show that estimating a standard credit demand equation with nonexperimental variation leads to seriously biased estimates even when conditioning on a rich set of controls and individual fixed effects. In particular, this procedure results in a large and statistically significant 3-month elasticity of credit card debt with respect to interest rates even though the experimental estimate of the same elasticity is neither economically nor statistically different from zero.