Some public programs jointly provide a mix of public goods and bads. Consequently, some individuals would pay for the program, while others would not, and might instead need compensation. We provide a parametric and a non-parametric modeling approach to estimate a net willingness to pay (WTP of gainers minus WTA of losers) for a non-rejectable mixed public-good/public-bad. We illustrate the models using data on valuation of prescribed burning of underbrush in forests, which reduces the risk of catastrophic wildfires but produces smoke emissions (the public bad). We compare the two empirical approaches to estimate the net WTP for the program.