Year: 2022
Type: article
Abstract: eat is a new package for R that includes functions to estimate production frontiers and technical efficiency measures through non-parametric techniques based upon regression trees. The package specifically implements the main algorithms associated with a recently introduced methodology for estimating the efficiency of a set of decision-making units in Economics and Engineering through Machine Learning techniques, called Efficiency Analysis Trees [@esteve2020]. The package includes code for estimating input- and output-oriented radial measures, input- and output-oriented Russell measures, the directional distance function and the weighted additive model, plotting graphical representations of the production frontier by tree structures, and determining rankings of importance of input variables in the analysis. Additionally, it includes the code to perform an adaptation of Random Forest in estimating technical efficiency. This paper describes the methodology and implementation of the functions, and reports numerical results using a real data base application.
Source: The R Journal
DOI: 10.32614/rj-2022-054
Institution: Universitat de Miguel Hernández d'Elx
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4320021560