Autoregressive stochastic frontier model with nonlinear function of exogenous variable and dynamic technical inefficiency

In this paper, we focus on a new autoregressive stochastic frontier model based on the nonlinear function of the exogenous variable in the panel data. In classical financial models, the technical inefficiency is considered uncorrelated, which is often not satisfied in empirical cases. In the proposed autoregressive stochastic frontier model, the error consists of two components, statistical error, and technical inefficiency, so that technical inefficiency is assumed to be autocorrelated. Autocorrelated technical inefficiency can be interpreted as the technical inefficiency of a company at the current time depends on the extent of the company's previous technical inefficiency and its current transient inefficiency. The semiparametric method for estimating the nonlinear function of the exogenous variable is calculated through a two-step process with Taylor series expansion and nonparametric adjustment factor. The expectation-maximization approach is used to estimate the parameters of the model and the estimation performance is evaluated by Monte Carlo simulation.