DEA and Monte Carlo simulation approach towards green car selection

Abstract

Purpose Automakers are engaged in manufacturing both efficient and inefficient green cars. The purpose of this paper is to categorize efficient green cars and inefficient green cars followed by improving efficiencies of identified inefficient green cars for distribution fitting. Design/methodology/approach The authors have used 2014 edition of secondary data published by the Automotive Research Centre of the Automobile Club of Southern California. The paper provides the methodology of applying data envelopment analysis (DEA) consisting of 50 decision-making units (DMUs) of green cars with six input indices (emission, braking, ride quality, acceleration, turning circle, and luggage capacity) and two output indices (miles per gallon and torque) integrated with Monte Carlo simulation for drawing significant statistical inferences graphically. Findings The findings of this study showed that there are 27 efficient and 23 inefficient DMUs along with improvement matrix. Additionally, the study highlighted the best distribution fitting of improved efficient green cars for respective indices. Research limitations/implications This study suffers from limitations associated with 2014 edition of secondary data used in this research. Practical implications This study may be useful for motorists with efficient listing of green cars, whereas automakers can be benefitted with distribution fitting of improved efficient green cars using Monte Carlo simulation for calibration. Originality/value The paper uses DEA to empirically examine classification of green cars and applies Monte Carlo simulation for distribution fitting to improved efficient green cars to decide appropriate range of their attributes for calibration.