ABSTRACT To enhance the decision-making process and reduce economic losses caused by future flooding, it is critical to quantify uncertainty in each step of flood risk analysis. To address the often-missing uncertainty quantification, we propose a new methodology that combines damage functions and probability bounds analysis. We estimate the likely direct tangible damage to 375,973 residential buildings along the Fraser River through Metro Vancouver, Canada, for a range of climate change driven flood scenarios, while transparently representing the associated uncertainties caused by sampling error, imprecise measurement, and uncertainty in building height and basement conditions. Furthermore, for the purposes of developing effective management strategies, uncertainties in this study are classified into two categories, namely aleatory and epistemic. According to our findings and absent significant action, we should expect an enormous increase in flood damage to the four categories of residential buildings considered in this study by the year 2100. Moreover, the results show that second-order Monte Carlo simulation cannot adequately represent epistemic uncertainty for small sample sizes. In such a case, we recommend employing a probability box to delineate the epistemic uncertainty.