Professional Documents
Culture Documents
2
In this application of DEA, a linear programming model
is developed for each hospital whose efficiency is to be
evaluated.
3
DEA Linear Programming Model
To determine the weight that each hospital will have in computing the
outputs and inputs for the composite hospital, we use the following
decision variables:
wg = weight applied to inputs and outputs for General Hospital
wu = weight applied to inputs and outputs for University Hospital
wc = weight applied to inputs and outputs for County Hospital
ws = weight applied to inputs and outputs for State Hospital
The DEA approach requires that the sum of these weights equal Thus,
the first constraint is
wg + wu + wc + ws = 1
4
ANNUAL SERVICES PROVIDED (OUTPUTS) BY THE FOUR HOSPITALS
Every DEA linear programming model will include a constraint that requires the weights for the operating
units to sum to 1.
5
for each output measure, the output for the composite hospital is determined by
computing a weighted average of the corresponding outputs for all four
hospitals. For instance, for output measure 1, the number of patient-days of
service under Medicare, the output for the composite hospital is:
Output for the Composite Hospital >= Output for County Hospital
6
RELATIONSHIP BETWEEN THE OUTPUT MEASURES FOR THE FOUR
HOSPITALS AND THE OUTPUT MEASURES FOR THE COMPOSITE HOSPITAL
7
Because the number of Medicare patient-days for County Hospital is
36.72, the output constraint corresponding to the number of Medicare
patient-days is
Formulated a constraint for each of the other three output measures, with
the results as shown:
8
Input for the Composite Hospital <= Resources available to the
Composite Hospital
For each input measure, the input for the composite hospital is a
weighted average of the corresponding input for each of the four
hospitals. Thus, for input measure 1, the number of full-time equivalent
nonphysicians, the input for the composite hospital is:
9
obtain the following expression for the number of full-time equivalent
nonphysicians for the composite hospital:
285.20wg + 162.30wu + 275.70wc + 210.40ws
10
RELATIONSHIP BETWEEN THE INPUT MEASURES FOR THE FOUR
HOSPITALS AND THE INPUT MEASURES FOR THE COMPOSITE HOSPITAL
11
the input constraint corresponding to the number of FTE nonphysicians
available to the composite hospital:
285.50wg + 162.30wu + 275.70wc + 210.40ws <= 275.70E
the input constraints for the supplies and bed-days are written as follows:
12
13
The Slack/Surplus column provides some additional information about the efficiency of
County Hospital compared to the composite hospital.
Specifically, the composite hospital has at least as much of each output as County Hospital
has (constraints 2–5) and provides 1.6 more nurses trained (surplus for constraint 4) and 37
more interns trained (surplus for constraint 5).
The slack of zero from constraint 8 shows that the composite hospital uses approximately
90.5% of the bed-days used by County Hospital.
The slack values for constraints 6 and 7 show that less than 90.5% of the FTE nonphysician
and the supplies expense resources used at County Hospital are used by the composite
hospital.
The composite hospital is more efficient than County Hospital, and we are justified in
concluding that County Hospital is relatively inefficient compared to the other hospitals in
the group.
Given the results of the DEA analysis, hospital administrators should examine operations to
determine how County Hospital resources can be more effectively utilized.
14
THE SOLUTION FOR THE COUNTY HOSPITAL DATA
ENVELOPMENT ANALYSIS PROBLEM
15
THE SOLUTION FOR THE COUNTY HOSPITAL DATA
ENVELOPMENT ANALYSIS PROBLEM (cont..)
16
Data Envelopment Analysis
17
Data Envelopment Analysis
Min E
s.t. Weighted outputs > Unit k’s output
(for each measured output)
Weighted inputs < E [Unit k’s input]
(for each measured input)
Sum of weights = 1
E, weights > 0
18
Data Envelopment Analysis
19
Data Envelopment Analysis
Input
20
Data Envelopment Analysis
Output
21
Data Envelopment Analysis
22
Data Envelopment Analysis
23
Data Envelopment Analysis
Output Constraints:
Since w1 = 1 is possible, each output of the composite
school must be at least as great as that of Roosevelt:
(2) 800w1 + 830w2 + 900w3 > 800 (SAT Scores)
(3) 450w1 + 500w2 + 400w3 > 450 (Graduates)
(4) 140w1 + 250w2 + 370w3 > 140 (College Admissions)
24
Data Envelopment Analysis
Computer Solution
26
Data Envelopment Analysis
Conclusion
The output shows that the composite school is made
up of equal weights of Lincoln and Washington.
Roosevelt is 76.5% efficient compared to this composite
school when measured by college admissions (because
of the 0 slack on this constraint #4).
It is less than 76.5% efficient when using measures
of SAT scores and high school graduates (there is
positive slack in constraints 2 and 3.)
27
End of Chapter 5, Part A
28