sdea {Benchmarking} | R Documentation |
Super efficiency
Description
The method sdea
calculates super-efficiency and
returns the same class of object as dea
.
Usage
sdea(X, Y, RTS = "vrs", ORIENTATION = "in", DIRECT = NULL, param = NULL,
TRANSPOSE = FALSE, LP = FALSE, CONTROL = NULL)
Arguments
X |
Inputs of firms to be evaluated, a K x m matrix
of observations of K firms with m inputs (firm x input). In case
| ||||||||||||||||||||||||
Y |
Outputs of firms to be evaluated, a K x n matrix
of observations of K firms with n outputs (firm x input). In case
| ||||||||||||||||||||||||
RTS |
Text string or a number defining the underlying DEA
technology / returns to scale assumption, the same values as for
| ||||||||||||||||||||||||
ORIENTATION |
Input efficiency "in" (1), output efficiency
"out" (2), and graph efficiency "graph" (3). For use with
| ||||||||||||||||||||||||
DIRECT |
Directional efficiency, If the argument is a scalar, the direction is (1,1,...,1) times the scalar; the value of the efficiency depends on the scalar as well as on the unit of measurements. If the argument an array, this is used for the direction for
every firm; the length of the array must correspond to the
number of inputs and/or outputs depending on the
If the argument is a matrix then different directions are used
for each firm. The dimensions depends on the
| ||||||||||||||||||||||||
param |
Argument is at present only used when
| ||||||||||||||||||||||||
TRANSPOSE |
See the description in | ||||||||||||||||||||||||
LP |
Only for debugging, see the description in
| ||||||||||||||||||||||||
CONTROL |
Possible controls to lpSolveAPI, see the
documentation for that package. For examples of use see the
function |
Details
Super-efficiency measures are constructed by avoiding that the evaluated firm can help span the technology, i.e. if the firm in qestuen is a firm on the frontier in a normal dea approach then this firm in super efficiency might be outside the technology set.
Value
The object returned is a Farrell object with the component
described in dea
. The relevant components are
eff |
The efficiencies. Note when DIRECT is used then the efficencies are not Farrell efficiencies but rather excess values in DIRECT units of measurement. |
lambda |
The lambdas, i.e. the weight of the peers, for each Firm. |
objval |
The objective value as returned from the LP program; normally the same as eff. |
RTS |
The return to scale assumption as in the option
|
ORIENTATION |
The efficiency orientation as in the call. |
Note
Calculation of slacks for super efficiency should be done by
using the option SLACK=TRUE
in the call of the method
sdea
. If the two phases are done in two steps as first a
call to sdea
and then a call to slacks
the user must
make sure to set the reference technology to the one corresponding
to super-efficiency in the call to slack
and this requires a
loop with calls to slack
.
Author(s)
Peter Bogetoft and Lars Otto larsot23@gmail.com
References
Peter Bogetoft and Lars Otto; Benchmarking with DEA, SFA, and R; Springer 2011. Sect. 5.2 page 115
P Andersen and NC Petersen; “A procedure for ranking efficient units in data envelopment analysis”; Management Science 1993 39(10):1261–1264
See Also
Examples
x <- matrix(c(100,200,300,500,100,200,600),ncol=1)
y <- matrix(c(75,100,300,400,25,50,400),ncol=1)
se <- sdea(x,y)
se
# Leave out firm 3 as a determining firm of the technology set
n <- 3
dea.plot.frontier(x[-n], y[-n], txt=(1:dim(x)[1])[-n])
# Plot and label firm 3
points(x[n],y[n],cex=1.25,pch=16)
text(x[n],y[n],n,adj=c(-.75,.75))