See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/321824482

Data Envelopment Analysis

Chapter · December 2017

CITATIONS READS

11 473

3 authors, including:

Chandrasekar Venu Sendhil Ramadas

Central Institute of Fisheries Technology, Kerala, India ICAR-Indian Institute of Wheat and Barley Research, Karnal, Haryana (India)
13 PUBLICATIONS   16 CITATIONS    106 PUBLICATIONS   215 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Market forecast centre View project

Tracking wheat yield sensitivity to weather variability across Indian transect for climate smart farming View project

All content following this page was uploaded by Sendhil Ramadas on 15 December 2017.

The user has requested enhancement of the downloaded file.

e-Compendium of Training-cum-Workshop on Data Analysis Tools and Approaches (DATA) in Agricultural Sciences
March 22-24, 2017

Data Envelopment Analysis

Chandrasekar V , Sendhil R and P Ramasundaram
1 2 3

1
ICAR-Central Institute of Fisheries Technology, Kochi-682029, Kerala
2
ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001, Haryana
3
National Agricultural Higher Education Project, New Delhi-110012

Data Envelopment Analysis (DEA)

DEA is a powerful optimisation tool used to measure the efficiency of any sectoral unit in
terms of both technical and allocative efficiency. It compares the DMUs to a target on the
frontier. The frontier is the best practice frontier based upon the current set. DEA is a
multiple criteria decision making tool, and before one applies DEA model he/she need to
choose a set of peer units, DMU’s (Decision Making Unit) in DEA, it means they are the units
under evaluation or benchmarking viz., farms, firms, hospitals, banks, universities, products,
cities, government, airlines etc. Ultimately DEA is intended as a method for performance
evaluation and benchmarking against best-practice.

Efficient Frontier: The line connecting the most efficient point is the efficient frontier called
‘frontier line’. Efficient frontier envelopes other data points, that’s why it is called as Data
Envelopment Analysis (DEA).
 The frontier line displays the performance of the unit in comparison to others.
 The efficiency of other unit can be measured by the deviation of points from the
frontier line. Efficiency of other units is measured relative to the efficient frontier.
 Efficient frontier serves as a benchmark.

The efficiency of any firm or unit consists of two components:

1. Technical efficiency: It means the ability of a firm to obtain maximum output from a
given set of inputs.
2. Allocative efficiency: It means the ability of a firm to use the inputs in optimal
proportions, given their respective prices.

In DEA, the efficiency or performance of DMU’s were measured in two ways:

1. Input-oriented model: It tries to see if the DMU can reduce its current input and still
producing the same amount of outputs.
2. Output-oriented model: It tries to see if the DMU can increase its current output
using current input level.

Return to scale (RTS) is often used to characterise the different DEA models. The different
types of DEA frontiers are as follows:
1. Constant RTS : CRS
2. Variable RTS : VRS (Constant, Increasing and Decreasing RTS)
3. Non-increasing RTS : NIRS
4. Non-decreasing RTS : NDRS

82 | ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001

e-Compendium of Training-cum-Workshop on Data Analysis Tools and Approaches (DATA) in Agricultural Sciences
March 22-24, 2017

The term ‘Efficiency’ is the ability of a firm to obtain maximum (minimum) outputs (inputs)
from a given set of inputs (outputs), whereas cost-efficiency requires achieving the lowest
possible cost, given the current prices and firm outputs. The figure given below depicts the
concept of cost efficiency where there are twelve DMUs labelled as A, B, C, . . .L and M with
two inputs and a single constant output with their respective prices. The input price ratio is
reflected by the slope of the iso-cost-line NN/ and the curve line connecting the points from
‘A’ to ‘M’ DMUs is the frontier line. The concept of frontier is especially important for the
analysis of efficiency, because we measure efficiency as the relative distance to the frontier.
For instance, the DMUs like B, D, G, I and K that are technically inefficient, operate at points
in the interior of the shaded region, while DMUs that are technically efficient, operate
somewhere along the technology defined by the frontier. So every package of inputs along
the frontier line is considered technically efficient, while any point above and to the right of
the frontier is technically inefficient producer, i.e. the DMU produces the same amount of
output, but with greater amounts of both inputs. For example, at point G the measure of
radial efficiency identifies the two points, G1 and G2 (Farrell, 1957) and defines the ‘technical
( , ) ( , ) ( , )
efficiency’, ‘allocative efficiency’ and ‘cost efficiency’ as ( , )
, ( , )
and ( , )
,
respectively. The multiplicative interaction of both technical efficiency (TE) and allocative
efficiency (AE), termed as overall economic efficiency (EE), is calculated as per Equation
(1):
( , ) ( , ) ( , )
EE = TE × AE = ( , )
× ( , )
= ( , )
…….. (1)

Cost efficiency method of DEA constant return to scale (Input-oriented)

, ,
Subject to - + ≥ 0,
− ≥ 0,
≥ 0, …. (2)

83 | ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001

e-Compendium of Training-cum-Workshop on Data Analysis Tools and Approaches (DATA) in Agricultural Sciences
March 22-24, 2017

where, is a scalar and is a Nx1 vector of constraints. This envelopment form involves
fewer constraints than the multiplier form ( + ) < ( + 1) , the value of is the efficiency
score for the ith DMU. It will satisfy ≤ 1, with a value of 1 indicating a point on the frontier
and hence a technically efficient DMU, according to the Farrell (1957) definition.

To calculate cost efficiency, prices of all the six inputs were used to study the behavioural
objective, such as cost minimization or profit maximization. For this, the mathematical form
of cost minimization DEA as represented in Equation (3) can be used:
, ∗
′ ∗
,
Subject to - + ≥ 0,
∗
− ≥ 0,
≥ 0, …. (3)

where, wi is a vector of input prices for the ith DMU and xi* is the cost minimizing vector of
input quantities for the ith DMU, given the input price wi and the output level yi. The total cost
efficiency (CE) or economic efficiency of the ith DMU is calculated by Equation (4):
CE = ′ ∗
, ′
. ….(4)

It is the ratio of minimum cost and observed cost. Using Equation (1) the allocative efficiency
(AE) can be calculated as:
AE = CE/TE

Steps in DEA Analysis

1. Collect the pooled data on Output and Input quantities and their respective values for
different DMU’s
2. Download the open source DEAP software from the Centre for Efficiency and
Productivity Analysis (CEPA) portal
(http://www.uq.edu.au/economics/cepa/deap.htm)
3. Install the DEAP
4. Arrange the dataset as per the requirement of DEAP (output first followed by inputs)
in *txt file
5. Modify the inbuilt instruction file and compute the Technical, Allocative and Economic
efficiency

In that DEAP folder we have create three type of txt file.

1. Instruction file - Eg1-ins.txt
2. Data file - Eg1-dta.txt
3. Output file - Eg1-out.txt

Instruction file: it can be modified according to our data taken for analysis whether it may
single output with multiple input situations or multiple outputs with single input or multiple
output with multiple input. For measuring allocative efficiency value of the inputs also have to
mention.

84 | ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001

e-Compendium of Training-cum-Workshop on Data Analysis Tools and Approaches (DATA) in Agricultural Sciences
March 22-24, 2017

eg3-dta.txt DATA FILE NAME

eg3-out.txt OUTPUT FILE NAME
5 NUMBER OF FIRMS
1 NUMBER OF TIME PERIODS
1 NUMBER OF OUTPUTS
2 NUMBER OF INPUTS
0 0=INPUT AND 1=OUTPUT ORIENTATED
0 0=CRS AND 1=VRS
1 0=DEA(MULTI-STAGE), 1=COST-DEA, 2=MALMQUIST-DEA, 3=DEA(1-
STAGE), 4=DEA(2-STAGE)

DEA: Illustrated Example using DEAP Software

Data has to be arranged in this format given below. Here the 1st column represent output
quantity, 2nd & 3rd column is input and 4th & 5th column represent input value
12513
22413
36613
13213
26213

Results from DEAP Version 2.1

Instruction file = eg3-ins.txt

Data file = eg3-dta.txt

Cost efficiency DEA

Scale assumption CRS

EFFICIENCY SUMMARY:

firm te ae ce
1 0.500 0.706 0.353
2 1.000 0.857 0.857
3 0.833 0.900 0.750
4 0.714 0.933 0.667
5 1.000 1.000 1.000

mean 0.810 0.879 0.725

Note: te = technical efficiency, ae = allocative efficiency = ce/te and ce = cost efficiency

SUMMARY OF COST MINIMISING INPUT QUANTITIES:

85 | ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001

View publication stats

e-Compendium of Training-cum-Workshop on Data Analysis Tools and Approaches (DATA) in Agricultural Sciences
March 22-24, 2017

firm input 1 2
1 3.000 1.000
2 6.000 2.000
3 9.000 3.000
4 3.000 1.000
5 6.000 2.000

Suggested Readings
Charnes A, Cooper W.W and Rhodes E. (1978) Measuring the efficiency of decision making
units, European Journal Operational Research, 2, 429 - 444.
Charnes, A., Cooper, W., Lewin, A., Y., and Seinfoud, L., M. (Eds) (1994) Data Envelopment
Analysis: Theory, methodology and applications. Boston, Kluwer. Data Envelopment
Analysis.
Coelli, T.J. (1996) A guide to DEAP Version 2.1: a data envelopment analysis (computer)
program. CEPA Working Papers – No. 8/96. Department of Econometrics, University
of New England, Armidale, Australia.
Coelli, T.J. (2008). A Guide to DEAP Version 2.1: A Data Envelopment Analysis (Computer)
Program (available at http://www.owlnet.rice.edu/~econ380/DEAP.PDF)
Cooper, W.W., Seiford, L.M., Tone, K. (2007) Data envelopment analysis: A comprehensive
text with models, applications, references and DEA-solver software. Kluwer Academic
Publishers, Boston, 318 pp.
Farrell, M.J. (1957) The measurement of productivity efficiency. Journal of the Royal
Statistical Society 120(3), 253-290.
Johansson, H. (2005) Technical, allocative, and economic efficiency in Swedish dairy farms:
the data envelopment analysis versus the stochastic frontier approach. Poster
background paper at 11th International congress of the European Association of
Agricultural Economists (EAAE), Copenhagen, Denmark, August 24-27, 2005, 17pp.
Ramanathan, R. (2003) An Introduction to Data Envelopment Analysis: A Tool for
Performance Measurement. Sage Publications India Pvt. Ltd, New Delhi.
Sendhil R, Thirumalvalavan V and T R Shanmugam (2006). Technical Efficiency of Crop
Production at Regional Level – An Application of Data Envelopment Analysis (DEA),
Indian Journal of Social Development, 6 (2): 289-299.
Subhash, C.R. (2004) Data envelopment analysis: Theory and techniques for economics
and operational research. Cambridge University Press, UK, 14p.

86 | ICAR-Indian Institute of Wheat and Barley Research, Karnal-132001