Sensitivity Analysis: Presented by BHARGAV SEERAM, 121202079
Sensitivity Analysis: Presented by BHARGAV SEERAM, 121202079
ANALYSIS
Presented by BHARGAV SEERAM, 121202079
DEFINITION
A technique used to determine how different values of an
in model components.
structure.
SYSTEM OSCILLATION
System oscillation is the characteristic symptom of negative
SYSTEM OSCILLATION
SENSITIVITY ANALYSIS IN
LITERATURE
In the study conducted by Ford (1990), sensitivity of results are
BEHAVIOR PATTERN
SENSITIVITY
Behavior measures are the subject matter of system dynamics
10
BEHAVIOR SENSITIVITY
ANALYSIS METHODOLOGY
SEPARATE
DIFFERENT
BEHAVIOR
MODES
Define
CHOOSE THE
ANALYSIS
PARAMETERS
OF THE
MODEL
DETERMINE
PARAMETER
RANGES AND
DISTRIBUTION
MAKE
SENSITIVITY
SIMULATION
S
EXPLORE
POSSIBLE
BEHAVIORS
Are
there
any
Differen
t
Behavio
r Modes
Behavior
Measure For
Each
Different
Behavior
MAKE
REGRESSION
ANALYSIS
FOR EACH
Calculate
MODE
Behavior
Pattern
Measures for
Each
Behavior
11
SENSITIVITY ANALYSIS
METHODS
Correlation & Screening Method
Regression Method
Another convenient method assuming linear relationship between
variables is regression.
In this method, an equation that minimizes the sum of squares of residual
terms is calculated by using ordinary least squares algorithm (Draper and
Smith, 1998).
When a nonlinear relationship is detected at the diagnosis of regression
12
SENSITIVITY ANALYSIS
METHODS (2)
Statistical Analysis (ANOVA) of Clusters in Scatter Plots
Another efficient way of dealing with nonlinearity between system output
and parameters is using statistical analysis of clusters in which output
variable y is plotted against each parameter xj and this plot is subject to
statistical analysis after it is divided into several clusters (Kleijnen and
Helton, 1999a).
This method is a more general way of one-variate sensitivity analysis
since it does not have the linearity assumption between dependent and
independent variables, i.e. this is a statistical model independent
method" (Saltelli et al., 2000).
The scatter plot for each parameter is subject to statistical analysis in
order to detect any non-random pattern.
13
Figure: Stock Flow Structure of Simple Supply Line Model by Sterman (2000)
14
SENSITIVITY ANALYSIS OF A
BASIC OSCILLATION SUPPLY
CHAIN
MODEL
Supply chains are good examples of material delay formulations that
Interaction between negative feedback loops and the time lag may
yield oscillations
15
amplitude slope.
troughs.
This pattern measure indicates how much the system oscillates under
certain circumstances.
16
SENSITIVITY ANALYSIS OF
OSCILLATION PERIOD
In this thesis, periods are estimated by autocorrelation function in BTSII
time lag in supply line. Increasing values of this parameter yields longerperiod oscillatory systems.
17
18
19
REFERENCES
A methodology for statistical sensitivity analysis of system dynamics
(www.Ie.Boun.Edu.Tr/labs/sesdyn/publications/theses/ms_hekimoglu.Pdf)
20