6. Conclusio
nWe presented a novel DEA toolkit for profitefficiency analysis inthe context of multi-output production. A distinguishing feature of ourmethodology is that it assumes output-specific production technolo-gies. In addition, the methodology accounts for the use of joint inputs,and explicitly includes information on the allocation of inputs tospecificoutputs.We have specified a multi-output profitinefficiency measure whenprices are observed, as well as a shadow profitinefficiency measurethat can be used if prices are unknown. Our framework also allows usto define output-specificprofitinefficiency measures, which allocate aDMU's aggregate profitinefficiency to individual outputs. Finally, weestablished a dual relationship between our multi-output profitinefficiency measure and a technical inefficiency measure that takesthe form of a multi-output directional distance function.