The overall aim of this paper is to discern whether and to what degree vaccination sites are not exhibiting constant returns to scale. Data Envelopment Analysis (DEA) was employed which allows for the comparison of all the facilities in the sample in terms of input costs utilized in producing multiple outputs. The approach was applied to the Expanded Program on Immunization (EPI) operating in Dhaka City, Bangladesh during 1999. It was found that a preponderance of EPI sites were operating at increasing returns to scale. The findings question the applicability of cost-effectiveness analyses that assume constant returns to scale.
International Journal of Technology Assessment in Health Care (2003) 19 (4) 692-697 [doi:10.1017/S0266462303000655]