Multifactor efficiency in Data Envelopment Analysis with an application to urban hospitals

A perennial difficulty in measuring hospital efficiency, and one with important policy implications, is how to compare teaching versus non-teaching hospitals. This problem reflects a broader methodological concern in Data Envelopment Analysis (DEA), which is the comparison of specialist and non-specialist Decision-Making Units (DMUs). This paper presents a new performance measure in DEA, termed multifactor efficiency, which represents an average partial factor productivity index summed over all output-input ratios. We apply this technique to measure the performance of 27 large, urban hospitals, including 13 teaching hospitals. These results were reviewed and validated by a panel of health care experts, and multifactor efficiency was shown to offer several benefits that enhance and complement existing performance measures in DEA.