Fertilizer subsidies are again becoming a popular policy tool in sub-Saharan Africa. Despite their potential, little empirical research has been undertaken on how subsidies affect a farmer’s decision to purchase commercial fertilizer. Because of this, there is a dearth of information on how fertilizer subsidy programs affect total fertilizer and commercial fertilizer use. This paper uses a double hurdle model with panel data from Malawi to answer these questions. It also uses a control function approach to deal with endogeneity of subsidized fertilizer in a commercial fertilizer demand equation. Our results indicate that subsidized fertilizer negatively impacts participation in commercial markets. Once the participation decision has been made however, demand for commercial fertilizer is driven by farm size, assets and fertilizer price and maize price rather than by whether a farmer received subsidized fertilizer. We calculate the average partial effects of subsidized fertilizer and find that on average, receiving one additional kilogram of subsidized fertilizer causes a farmer to purchase 0.20 fewer kilograms of commercial fertilizer. This indicates that fertilizer subsidies may adversely affect the demand for commercial fertilizer and also raise total fertilizer use by a somewhat smaller quantity than the quantity of fertilizer distributed through the subsidy program.