DATA ENVELOPMENT ANALYSIS IN THE PRESENCE OF BOTH QUANTITATIVE AND QUALITATIVE FACTORS

This paper presents a framework for incorporating ordinal data factors into the standard ratio DEA model. An application involving the prior itization of R&D projects is presented as a case in point where such o rdinal factors appear in a natural way. Two different models for incor porating ordinal data are developed; one in which the ordinal factors are ranked and one where they are not. Finally, the issue of selecting a lower bound epsilon on factors is addressed.