Data Envelopment Analysis (DEA) applications frequently involve nonsubstitutable inputs and nonsubstitutable outputs (that is, fixed proportion technologies). However, DEA theory requires substitutability. In this paper, we illustrate the consequences of nonsubstitutability on DEA efficiency...

We describe a statistical method for estimating DEA score confidence intervals, and illustrate it with panel data of large US transit agencies from the years 2002-2006. The method applies statistical panel data analysis (PDA), which provides proven and powerful methodologies for diagnostic...

In Data Envelopment Analyses (DEA) of fossil-fuel electricity generating plants, the most common input measures are installed generator capacity (as a proxy for capital), number of employees (as a proxy for labor), and BTUs of fuel (as a proxy for energy). However, these three inputs cannot be...