Case Study: Data Envelopment Analysis

Back to main page
Case study background and problem formulations

Instructions for optimization with PSG Run-File, PSG MATLAB Toolbox, PSG MATLAB Subroutines and PSG R.

PROBLEM1: problem_linear
maximizing Linear
subject to
Ax ≤0 (multiple linear constraints ensuring that for all companies efficiency is not higher than 1)
d’x=1 (constraint maintaining denominator of ratio for company k = 0 equal to 1)
Box constraints (lower and upper bounds on variables)
——————————————————————–——————
Linear = Linear function
Box constraints = constraints on individual decision variables
——————————————————————–——————
Data and solution in Run-File Environment

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 2.83GHz (sec)
Dataset1 Problem statement Data Solution 6 5 0.58433 <1
Dataset2 Problem statement Data Solution 6 5 0.81256 <1
Dataset3 Problem statement Data Solution 6 5 1.00000 <1
Dataset4 Problem statement Data Solution 6 5 0.76799 <1
Dataset5 Problem statement Data Solution 6 5 0.85086 <1
Data and solution in MATLAB Environment

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 3.50GHz (sec)
Dataset1 Matlab code Data Solution 6 5 0.58433 <1
Dataset2 Matlab code Data Solution 6 5 0.81256 <1
Dataset3 Matlab code Data Solution 6 5 1.00000 <1
Dataset4 Matlab code Data Solution 6 5 0.76799 <1
Dataset5 Matlab code Data Solution 6 5 0.85086 <1
PROBLEM2: problem_max_risk
maximizing Linear
subject to
max_risk≤0 (constraint ensures that for all companies efficiency is not higher than 1)
d’x=1 (constraint maintaining denominator of ratio for company k = 0 equal to 1)
Box constraints ( lower and upper bounds on variables)
——————————————————————–——————
max_risk = maximum risk function
Box constraints = constraints on individual decision variables
——————————————————————–——————
Data and solution in Run-File Environment

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 2.83GHz (sec)
Dataset1 Problem statement Data Solution 6 5 0.58433 <1
Dataset2 Problem statement Data Solution 6 5 0.81256 <1
Dataset3 Problem statement Data Solution 6 5 1.00000 <1
Dataset4 Problem statement Data Solution 6 5 0.76799 <1
Dataset5 Problem statement Data Solution 6 5 0.85086 <1
Data and solution in MATLAB Environment

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 3.50GHz (sec)
Dataset1 Matlab code Data Solution 6 5 0.58433 <1
Dataset2 Matlab code Data Solution 6 5 0.81256 <1
Dataset3 Matlab code Data Solution 6 5 1.00000 <1
Dataset4 Matlab code Data Solution 6 5 0.76799 <1
Dataset5 Matlab code Data Solution 6 5 0.85086 <1
PROBLEM3: problem_linear _in_one_shot
For 5 problems
maximizing Linear
subject to
Ax ≤0 (multiple linear constraints ensuring that for all companies efficiency is not higher than 1)
d’x=1 (constraint maintaining denominator of ratio for company k = 0 equal to 1)
Box constraints (lower and upper bounds on variables)
end for
——————————————————————–——————
Linear = Linear function
Box constraints = constraints on individual decision variables
——————————————————————–——————
Download Problem Data

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 2.83GHz (sec)
Dataset1 Cycle statement Data Solution 6 5 0.58433 <1
Dataset2 6 5 0.81256 <1
Dataset3 6 5 1.00000 <1
Dataset4 6 5 0.76799 <1
Dataset5 6 5 0.85086 <1
PROBLEM4: problem_max_risk_in_one_shot
For 5 problems
maximizing Linear
subject to
max_risk≤0 (constraint ensures that for all companies efficiency is not higher than 1)
d’x=1 (constraint maintaining denominator of ratio for company k = 0 equal to 1)
Box constraints ( lower and upper bounds on variables)
end for——————————————————————–——————
max_risk = maximum risk function
Box constraints = constraints on individual decision variables
——————————————————————–——————Download Problem Data< 650.81256<1

Problem Datasets # of Variables # of Rows Objective Value Solving Time, PC 2.83GHz (sec)
Dataset1 Cycle statement Data Solution 6 5 0.58433 <1
Dataset2 6 5 0.81256 <1
Dataset3 6 5 1.00000 <1
Dataset4 6 5 0.76799 <1
Dataset5 6 5 0.85086 <1

 

CASE STUDY SUMMARY
This case study compares the relative managerial efficiency of five companies by applying the CCR Model from Data Envelopment Analysis (DEA) (Charnes et al, 1978). The comparison is made for the companies, Sempra Energy, American Electric Power Co., Inc., AGL Resources Inc., CenterPoint Energy, Inc. and Duke Energy Corporation from Utilities industrial sector. We used Earnings per Share, Debt to Equity Ratio, Leverage Ratio, Solvency Ratio as inputs and Net Profit Margin and Price to Earnings Ratio as outputs (collected from the financial statements of these companies). The categorization of inputs and outputs was made according to Zhang, 2007. The model maximize the ratio of the weighted outputs and the weighted inputs of the company for every company, subject to constraints prohibiting that the ratio of the other companies to be higher than 1.
For further readings about DEA, consult “Handbook on data envelopment analysis” from Cooper and “Service Productivity Management: Improving Service Performance Using Data Envelopment Analysis (DEA)” from Sherman.
The optimization problem is solved with two equivalent formulations utilizing the Multilinear and Max_Risk PSG functions.
References
• Charnes, A., Cooper, W. W. , and E. Rhodes (1978): “Measuring the efficiency of decision making units.” European Journal of Operational Research.
• Cooper, W.W, Lawrence M. S, and Z. Joe. (2011): “Handbook on data envelopment analysis”. Springer.
• Sherman, H. D. (2006): “Service Productivity Management: Improving Service Performance Using Data Envelopment Analysis (DEA). Includes DEAFrontier Software”. Springer.
• Zhang, X. (2007): “The Generalized DEA Model of Fundamental Analysis of Public Firms, with Application to Portfolio Selection.”. Doctoral Dissertation, University of Tennesse – Knoxville