Federal wildland fire management policy in the United States directs the use of value-based methods to guide priorities. However, the economic literature on the effect of wildland fire on nonmarket uses, such as recreation, is limited. This paper introduces a new approach to measuring the effect of wildfire on recreational use by utilising newly available long-term datasets on the location and size of wildland fire in the United States and observed behaviour over time as revealed through comprehensive National Park Service (NPS) visitor data. We estimate travel cost economic demand models that can be aggregated at the site-landscape level for Yellowstone National Park (YNP). The marginal recreation benefit per acre of fire avoided in, or proximate to, the park is US$43.82 per acre (US$108.29 per hectare) and the net present value loss for the 1986-2011 period is estimated to be US$206 million. We also estimate marginal regional economic impacts at US$36.69 per acre (US$90.66 per hectare) and US$159 million based on foregone non-resident spending in the 17-county Great Yellowstone Area (GYA). These methods are applicable where time-series recreation data exist, such as for other parks and ecosystems represented in the 397-unit NPS system.