On the use of panel data in stochastic frontier models with improper priors

We consider a Bayesian analysis of the stochastic frontier model with composed error. Under a commonly used class of (partly) noninformative prior distributions, the existence of the posterior distribution and of posterior moments is examined. Viewing this model as a Normal linear regression model with regression parameters corresponding to both the frontier and the inefficiency terms, generates the insights used to derived results in a very wide framework. It is found that in pure cross-section models posterior inference is precluded under this ‘usual’ class of priors. Existence of a well-defined posterior distribution then crucially hinges upon the structure imposed on the inefficiency terms. Exploiting panel data naturally suggests the use of more structured models, where Bayesian inference can be conducted.