Methodological considerations upon Stochastic Frontier Analysis for panel data models: evidence from cost-efficiency ECF model in the Argentine Banking Sector.

In this paper we make a methodological analysis of the Error Components Frontier (ECF) panel data model performance based on Stochastic Frontier Analysis (SFA) method for cost efficiency benchmarking in the presence of small panels and outliers. By means of a set of simulations and a subsequent application to the Argentine banking sector during the period 2005-2014, we prove that under these conditions an SFA model may not be adequate for benchmarking. These results are relevant for the empirical literature since small panels with the presence of outliers represent classical scenarios in developing economies industries. Reception date: December 3, 2019.Acceptance date: June 28, 2021.

• Main Authors: Girela, Ignacio G., Vargas, José M.
• Format: Online
• Language: spa
• Published: Instituto de Economía y Finanzas. Facultad de Ciencias Económicas. Universidada Nacional de Córdoba. 2021
• Subjects: panel data; SFA; banking entities; benchmarking; simulations; Semiparametric and Nonparametric Methods: General; Panel Data Models; Cost; Banks; Economics of Regulation; datos de panel; eficiencia orientada a costos; entidades bancarias; simulaciones; Métodos Semiparamétricos y No Paramétricos; Modelos de Datos de Panel; Costo; Bancos; Economía de la Regulación
• Online Access: https://revistas.unc.edu.ar/index.php/REyE/article/view/36335