• Thesis to Book with ISBN
• Aim And Scope
• Article in Press
• Editorial Board
• Current Issue
• Archives
• Publication Charges
• Authors Information
• Contact Us
• Paper Format

[Abstract] [PDF] [HTML] [Linked References]

International Journal of Statistika and Mathematika, ISSN: 2277- 2790 E-ISSN: 2249-8605

Volume 8, Issue 2, December 2013 pp 60-70

Research Article

Evaluation of Efficiency and Benchmarking Commercial Banks in India: A Combined PCA and DEA Approach

R. Chandrasekaran^1a, R. Madhana Gopal^2b

¹Professor and Head (Retired), ²Assistant Professor, Department of Statistics

Academic Editor:  Dr. Dase R.K.

Data Envelopment Analysis (DEA) is a non-parametric linear programming technique used to determine the relative efficiency of Decision Making Units (DMU’s).  To evaluate efficiency, multiple input and output variables are used.  There are exciting opinions available in the literature relating to the use of various input and output variables in assessing performance of DMU’s.  Even though there is no limit on the number of variables, the use of excessive number of variables will tend to reduce the discriminatory power within efficient as well as inefficient DMU’s.  In order to keep the number of input and output variables to a manageable level, it is possible to combine Principal Component Analysis (PCA) with DEA.  In this paper, PCA is applied first to all inputs and outputs separately.  With the intention to reduce the number of variables in the analysis, the principal components are chosen appropriately.  Then PCA scores of selected principal components are treated as input and output variables for DEA and the performance of commercial banks in India are determined.