The StoNED age: the departure into a new era of efficiency analysis? A monte carlo comparison of StoNED and the “oldies” (SFA and DEA)

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. The working papers published in the Series constitute work in progress circulated to stimulate discussion and critical comments. Views expressed represent exclusively the authors' own opinions and do not necessarily refl ect those of the editors. Terms of use: Documents in Ruhr Economic Papers #394

Operational Conditions in Regulatory Benchmarking Models: A Monte Carlo Analysis

“…StoNEZD performs well in cases with considerable noise, and especially in cases with a strong noise-to-signal ratio, i.e., low inefficiency, which is in line with the finding by Andor and Hesse (2014) for the standard StoNED without z-variables. StoNEZD performs worse than its competitors in cases with high inefficiency and very low noise.…”

“…9 We consider the bias and the mean squared error (MSE) as the criteria following the literature on simulation design in efficiency analysis (e.g., Andor and Hesse, 2014;Kuosmanen et al, 2013). The bias delivers the average total deviation from the true frontier in percentage.…”

“…Studies of the newer semi-parametric approaches include Andor and Hesse (2014), who find StoNED to perform well in noisy settings compared to SFA and DEA, but also a stronger sensitivity of StoNED against an increasing number of explanatory variables and a general tendency to underestimate the true frontier. Krüger (2012) compares the semi-parametric order-m and order-α estimators with DEA, Free Disposable Hull (FDH) and SFA, but finds no advantage in using them for well behaved production settings and low levels of noise.…”

Analysis of Interval Data Envelopment Efficiency Model Considering Different Distribution Characteristics—Based on Environmental Performance Evaluation of the Manufacturing Industry

“…Furthermore, the confidence region or level was introduced into the stochastic DEA model, e.g., by [44][45][46][47][48]. The Monte Carlo simulation algorithm was used to solve the problem of stochastic input and output variables and the study of stochastic DEA is one of the directions of current research, such as studies by [49][50][51][52][53][54]. The stochastic DEA model including the Bayesian method, such as in studies by [55][56][57][58][59][60], was used to deduce the efficiency value of a finite sample.…”

Pseudolikelihood estimation of the stochastic frontier model

“…Furthermore, its performance has never been properly adjudicated against ML. To date, studies that provide Monte Carlo simulation evidence regarding the PL estimator are Andor & Hesse (2014), Badunenko, Henderson & Kumbhakar (2012) and Fan et al (1996), which all focus on the nonparametric setting.…”