Corporate performance measurement using an integrated approach: A mongolian case

Abstract

The main goal of the study is to calculate the relevant efficiency scores of companies listed on the Mongolian Stock Exchange based on their efficiency scores. We apply an integrated principal component analysis (PCA) and data envelopment analysis (DEA) model to estimate corporate efficiency. The objective of using this integrated method to reduce the dimensionality of the dataset analysed and to evaluate companies’ efficiencies reliably. The number of variables using in the DEA model affects the results directly because of the DEA method is sensitive to the number of input and output variables. The PCA method can reduce the number of variables so that the information loss would be the smallest. The research uses one hundred publicly-listed Mongolian companies’ financial statements of 2015. Initially, DEA is applied conventionally using seven input and four output variables. Then, PCA is applied with the same variables to determine Principal Component (PC) scores, which are used for DEA as variables to improve its discrimination power. The results of the conventional DEA and the PCA-DEA models are compared to evaluate the consistency. The results of the inputoriented DEA model (under variable return to scale) determined 54 efficient companies, and the average efficiency scores were 0.73. However, PCADEA method diagnosed only five efficient companies, and the average efficiency was 0.65. Based on the results, we can state that the PCA-DEA method provides a more accurate picture of the real performance of the analysed companies.