Persistent and transient inefficiency in a spatial autoregressive panel stochastic frontier model

In this paper, we extend the four-component stochastic frontier model to allow for global spatial dependence via the endogenous spatial autoregressive variable. Our proposed model is more general than the model considered by (Glass et al., 2016 ) in the sense that we include a random effect as well...

Full description

Saved in:
Bibliographic Details
Published in:Journal of productivity analysis 2022-08, Vol.58 (1), p.1-13
Main Authors: Lai, Hung-pin, Tran, Kien C.
Format: Article
Language:English
Subjects:
Accounting/Auditing
Econometrics
Economics
Economics and Finance
Efficiency
Microeconomics
Operations Research/Decision Theory
Productivity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we extend the four-component stochastic frontier model to allow for global spatial dependence via the endogenous spatial autoregressive variable. Our proposed model is more general than the model considered by (Glass et al., 2016 ) in the sense that we include a random effect as well as a permanent efficiency component. With the spatial autoregressive specification, our model is able to capture the asymmetric efficiency spillovers and also decompose the persistent/transient inefficiencies into direct and indirect efficiencies. Moreover, we also investigate the marginal effects of the exogenous variables on the persistent/transient efficiency. We suggest a maximum simulated likelihood method to estimate the frontier parameters of the model, and we predict the efficiencies using the simulated estimator. Monte Carlo simulations reveal that the suggested estimator performs well in finite samples. An empirical application is considered to illustrate the usefulness of our proposed model and method.
ISSN:0895-562X
1573-0441
DOI:10.1007/s11123-022-00638-z