ACox nonnested test is conducted using a fast double bootstrap (FDB) method to select among three competing functional forms (linear response plateau, quadratic, and Mitscherlich-Baule) to model forage yield response to nitrogen applied with swine effluent. The quadratic is rejected in favor of one of the other functional forms in all cases. The FDB p values differed slightly from the single bootstrap p values. Buffalograss was slightly more profitable than bermudagrass and has the ability to use almost as much nitrogen as bermudagrass.