| The purpose of this Dissertation was to evaluate the robustness of Data Envelopment Analysis (DEA) with sensitivity analysis for assessing hospitals' efficiency using Jordan as a case study. The robustness of DEA was evaluated using two DEA models: CCR and BCC, with different input-output combinations. Sensitivity analysis was also used to evaluate the stability of efficiency scores of these DEA models. Two other methods, Cobb-Douglas and Ratio Analysis were also used in this study to evaluate hospitals' efficiency. The results were compared to those of DEA models. Finally, this study evaluated the efficiency of both private and public hospitals in Jordan. In addition to that, public hospitals in big cities were compared with those of small towns.; The data for this study were obtained for the years 1994 and 1995, from the Ministry of Health in Jordan, Royal Medical Services, and the Jordanian Private Hospitals Association. The original set consisted of all hospitals of the Ministry of Health and all private hospitals in Jordan. Specialized teaching and private not-for-profit hospitals were excluded in order to have a homogenous group of hospitals.; The findings indicate that the DEA results were stable and consistent for a majority of the hospitals. However, it was interesting to note that the differences in hospitals' classification were more distinguishable in the case of comparing DEA models (CCR and BCC) than that of input-output combinations. Additionally, the results indicate that the three methods; DEA, Cobb-Douglas, and Ratio Analysis fully agreed on classification of only 16.6% of the total number of hospitals. Finally, it was found that private hospitals were more efficient than public hospitals. Moreover, public hospitals in big cities were found to be more efficient than those in small towns. |
