We develop a series of novel conceptual tools to systematically account for errors-in-variables in Data Envelopment Analysis (DEA). These tools allow for statistical inference while requiring minimal statistical distribution assumptions, and therefore constitute a valuable addition to the tools...

The literature on non-parametric production analysis has formulated tests for profit maximizing behavior that do not require a parametric specification of technology. Negative test results have conventionally been interpreted as inefficiency, or have been attributed to data perturbations. In...