Scribd
Upload
172 views

Monte Carlo Simulation

Monte Carlo simulation is a technique used to model risk in complex systems where experiments may not be possible or practical. It differs from conventional mathematical modeling by using probability distributions to represent input variables rather than single values. The output of a Monte Carlo simulation is itself a probability distribution that accurately reflects the distributions of the input variables and the mathematical model or metric being used. This allows Monte Carlo simulation to provide a realistic representation of uncertainty and risk in systems being analyzed.

Uploaded by

Dejan Loncarevic
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
172 views

Monte Carlo Simulation

Monte Carlo simulation is a technique used to model risk in complex systems where experiments may not be possible or practical. It differs from conventional mathematical modeling by using probability distributions to represent input variables rather than single values. The output of a Monte Carlo simulation is itself a probability distribution that accurately reflects the distributions of the input variables and the mathematical model or metric being used. This allows Monte Carlo simulation to provide a realistic representation of uncertainty and risk in systems being analyzed.

Uploaded by

Dejan Loncarevic
Copyright
© © All Rights Reserved
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 10

Monte Carlo Simulation

and Risk Analysis


James F. Wright, Ph.D.

Monte Carlo Simulation


Scientific Uses
Complex Systems Where Experiments
are not Possible or Practical
Space Program
Nuclear and Thermonuclear Weapons
Catastrophic Mechanical Systems Design
Chemical & Nuclear Reactions

Monte Carlo Simulation


Economic Systems

It is Fiduciary Insurance!
Verify Economic Predictions
Investment Risk Analysis
Portfolio Management

Mathematical Simulation
Lets
Letsconsider
considerConventional
ConventionalMathematical
MathematicalSimulation,
Simulation,or
orModeling,
Modeling,ofofReal
RealSystems.
Systems.

In the Study of Mathematics we


Represent Real Systems
with an Equation, or Metric.
The
that
They,y,isisthe
theanswer
answer
Now
lets
that
examine
how
Monte
Carlo
Simulation
The
f f(x(xi) )isisthe
Mathematical
Now
lets
examine
how
Monte
Carlo
Simulation
The
the
Mathematical
i
represents
of
the
representsthe
thestate
state
differs
from
of
the
regular
Mathematical
Simulation
i
function
that
differs from regular Mathematical
Simulation
function
thatuses
usesthe
theInput
Input
Real
System
we
are
Real System we are
Variables,
Variables,xxi,i,totoproduce
producethe
the
modeling.
modeling.
answer,
answer,y.y.

y = f (x )

Monte Carlo Simulation


We recognize that the values of Input Variables for
our Metrics are seldom, if ever, exactly known.
Therefore, we use Realistic Distribution
Functions to Represent the Values of these Input
Variables.
By Sampling these Distribution Functions in a
Random Manner, our Answer is a Discrete
Distribution Function that accurately and
precisely represents both the Metric and the Input
Distribution Functions.

Distribution Function
It is a Frequency Distribution that is Normalized
(The Area under the Curve is equal to one). A
common example is the Bell Curve.
It can be Represented by either its pdf (Probability
Density Function) or cdf (Cumulative Distribution
Function).
It may be either Continuous or Discrete
(See my Book on the Subject)

Monte Carlo Simulation


In the Monte Carlo Method we
Represent Real Systems
with an Equation, or Metric.
Now
Nowlets
letssummarize
summarizeour
ourMonte
MonteCarlo
CarloModel.
Model.
The
TheAnswer
Answertotoour
ourMetric,
Metric,
yyk, ,isisaadiscrete
discrete
k
Distribution
DistributionFunction
Function
rather
than
a
rather than asingle
singlevalue!
value!

yk = f [g(xi)]

Each
EachInput
InputVariable
Variableisisnow
now
represented
by
a
realistic
represented by a realistic
Distribution
DistributionFunction,
Function,g(x
g(xi),i),
rather
ratherthan
thansingle-valued
single-valued
variables.
variables.

Monte Carlo Simulation


ItItisisimportant
importanttotonote
notethat
thatininorder
orderfor
forthe
theyyk ktotobe
berealistic,
realistic,both
bothofofthe
thefollowing
followingmust
mustbe
betrue.
true.
The
Monte
Carlo
method
uses
Distribution
Functions,
g
(x),
to
represent
each
Input
Variable
1.1.The
Each
ofofthe
individual
input
must
accurately
and
precisely
represent
Monte
Carlo
method
usesdistribution
Distributionfunctions
Functions,
gi i(x),
to represent
Input
Variable
Each
the
individual
input
distribution
functions
must
accurately
andeach
precisely
represent
ininthe
the
Metric
used
data.
theinput
Metric
usedtotoSimulate
Simulatethe
theReal
RealSystem.
System.The
TheMonte
MonteCarlo
Carlosolution
solutiontotothe
theMetric
Metricisisaa
the
input
data.
Distribution,
yyk , ,that
isisrepresentative
ofofboth
the
Metric,
and
Input
2.Discrete
The
or
must
realistically
represent
modeled.
Distribution,
representative
boththe
theprocess
Metric,being
andthe
the
InputDistribution
Distribution
2.Discrete
Themetric,
metric,
orequation,
equation,
must
realistically
represent
the
process
being
modeled.
k that
Functions.
Functions.(See
(Seemy
myBook
Bookon
onthe
theSubject)
Subject)

Rather
Ratherthan
thanuse
useaaBest
Bestsingle
singleValue
Valuefor
forthe
theInput
Inputvariables
variablesofofthe
themetric,
metric,we
werepresent
representeach
each
with
a
Distribution
Function.
This
Distribution
Function
includes
the
unique
Absolute
with a Distribution Function. This Distribution Function includes the unique Absolute
Minimum
MinimumValue,
Value,Absolute
Absolute Maximum
MaximumValue,
Value,and
andall
allpoints
pointsininbetween
betweenincluding
includingthe
theBest
Best(or
(or
Most
Likely)
Value.
The
calculated
answer
is
represented
by
a
Discrete
Probability
Most Likely) Value. The calculated answer is represented by a Discrete Probability
Distribution
Distributionthat
thatAccurately
Accuratelyand
andPrecisely
Preciselyreflects
reflectsthe
thecumulative
cumulativeeffects
effectsofofeach
eachofofthe
theInput
Input
Variables
and
the
Metric.
Variables and the Metric.

This
ThisBook
Bookapplies
appliesthe
thegeneral
generaltechnique
techniqueofofMonte
MonteCarlo
CarloSimulation
Simulationtotothe
theevaluation
evaluationofof
Business
BusinessProspects.
Prospects.However
Howeveras
asshown
shownininthis
thisbrief
briefpresentation,
presentation,the
thetechnique
techniquecan
canbe
be
applied
appliedtotoany
anymathematical
mathematicalfunction
functionyou
youare
areusing
usingtotomodel
modelyour
yourreal
realphysical
physicalsystem.
system.

Monte Carlo Simulation

James F. Wright, Ph.D.


432-367-1542
[email protected]

You might also like