When the allocated fixed cost is treated as the complement of other costs, conventional data envelopment analysis(DEA) researches have ignored the effect of the return to scale(RTS) in fixed cost allocation problems. This paper first demonstrates why the RTS should be considered in fixed cost allocation problems. Then treating the fixed cost as a complementary input, the authors investigate the relationship between the allocated cost and the variable return to scale(VRS) efficiency based on the super BCC DEA model. However, the infeasibility problem may exist in this situation.To deal with it, the authors propose an algorithm. The authors find that the super BCC efficiency is a monotone non-increasing function of the allocated cost. Based on the relationship, the authors finally propose a fixed cost allocation approach in terms of principles as:(i) The fixed cost proportion allocated to inelastic DMUs should be consistent with their consumed cost proportion, and(ii) the same efficiency satisfaction degree to the rest DMUs. The optimal allocation scheme is unique. A numerical example and a real example of allocating fixed costs among 13 subsidiaries are employed to illustrate the proposed approach. When the allocated fixed cost is treated as the complement of other costs, conventional data envelopment analysis (DEA) researches have ignored the effect of the return to scale (RTS) in fixed cost allocation problems. This paper first demonstrates why the RTS should be considered in fixed cost allocation problems. The treating of fixed costs as a complementary input, the authors investigate the relationship between the allocated cost and the variable return to scale (VRS) efficiency based on the super BCC DEA model. However, the infeasibility problem may exist in this situation. Deal with it, the authors propose an algorithm. The authors find that the super BCC efficiency is a monotone non-increasing function of the allocated cost. Based on the relationship, the authors finally propose a fixed cost allocation approach in terms of principles as: (i) The fixed cost proportion allocated to inelastic DMUs should be consistent with their consumed cost proportion, and (ii) the same efficiency A numerical example and a real example of allocating fixed costs among 13 subsidiaries are employed to illustrate the proposed approach.