fin 685: risk management topic 5: simulation larry schrenk, instructor
Post on 19-Dec-2015
215 views
TRANSCRIPT
FIN 685: Risk Management
Topic 5: Simulation
Larry Schrenk, Instructor
TOPICS
Why Simulation?
Monte Carlo Simulation
Example: European Call
SOLUTION TYPES
Closed Form– FV = PV(1+r)t
Numerical– Algorithm– Binomial Option Pricing
Simulation
Definition:“Simulation is the process of designinga model of a real system and conductingexperiments with this model for thepurpose of either understanding the behavior of the system and/or evaluating various strategies for theoperation of the system.” - Introduction to Simulation Using SIMAN (2nd Edition)
5 of 50
WHAT IS SIMULATION?
• Simulation is the use of a computer to evaluate a system model numerically, in order to estimate the desired true characteristics of the system.
• Simulation is useful when a real-world system is too complex to allow realistic models to be evaluated analytically.
WHY SIMULATION
Complexity/Flexibility Real World Applications Dependencies Descriptive Model Distributional Assumptions– Distributions not Tractable– Empirically Based Distributions
7 of 50
BASICSSystem: The physical process of interest
Model: Mathematical representation of the system– Models are a fundamental tool of science,
engineering, business, etc.– Abstraction of reality– Models always have limits of credibility
Simulation: A type of model where the computer is used to imitate the behavior of the system
Monte Carlo Simulation: Simulation that makes use of internally generated (pseudo) random numbers
CLASSIFICATIONStatic vs. dynamic
– Static: E.g., Simulation solution to integral – Dynamic: Systems that evolve over time; simulation
of traffic system over morning or evening rush period
Deterministic vs. stochastic– Deterministic: No randomness; solution of complex
differential equation in aerodynamics – Stochastic (Monte Carlo): Operations of store with
randomly modeled arrivals (customers) and purchases
Continuous vs. discrete– Continuous: Differential equations; “smooth” motion
of object – Discrete: Events occur at discrete times; queuing
networks
WAYS TO STUDY SYSTEM
System
Experiment w/ actual system
Experiment w/ model
Physical Model
MathematicalModel
Analytical Model
SimulationModel
MONTE CARLO SIMULATION The process of generating a
sequence of random values from a probability distribution
– Formal Distribution
– Empirical Distribution
USES
General Motors, Proctor and Gamble, Pfizer, Bristol-Myers Squibb, and Eli Lilly use simulation to estimate both the average return and the risk factor of new product
Sears uses simulation to determine how many units of each product line should be ordered from suppliers.
Financial planners use Monte Carlo simulation to determine optimal investment strategies for their clients’ retirement.
ADVANTAGES
1. It is relatively straightforward and flexible2. Recent advances in computer software
make simulation models very easy to develop
3. Can be used to analyze large and complex real-world situations
4. Allows “what-if?” type questions5. Does not interfere with the real-world
system6. Enables study of interactions between
components7. Enables time compression8. Enables the inclusion of real-world
complications
DISADVANTAGES
1. It is often expensive as it may require a long, complicated process to develop the model
2. Does not generate optimal solutions, it is a trial-and-error approach
3. Requires managers to generate all conditions and constraints of real-world problem
4. Each model is unique and the solutions and inferences are not usually transferable to other problems
SIMULATION STEPS
1. Define a problem2. Introduce the variables associated with
the problem3. Construct a numerical model4. Set up possible courses of action for
testing5. Run the experiment6. Consider the results7. Decide what courses of action to take
MONTE CARLO SIMULATION1. Determine
1. Probability Distribution 2. Dependencies
2. Generate Random Variables3. Find Terminal Values4. Discount5. Average
1. Probability Distributions
DETERMINE DISTRIBUTIONS AND DEPENDENCIES Sources– Historical Data– Surveys– Judgment– Theory
Misc– Goodness-of-Fit Software
2. Generate Random Numbers
EMPIRICAL DISTRIBUTION
PSEUDO RANDOM NUMBERS Statistical Qualities Excel: RAND()– Returns an evenly distributed
random real number greater than or equal to 0 and less than 1
– RAND()*(b-a)+a
DATA ANALYSIS PACK
Data > Data Analysis (Add-In)
THEORETICAL DISTRIBUTION
3. Find (Terminal) Value
TERMINAL VALUE OF STOCK What is the Stock Price for each
Trial?
0 0 0fS S r t S tRV
TERMINAL VALUE OF STOCK St
TERMINAL VALUE OF CALL MAX[St – X, 0]
4. Discount
PRESENT VALUE
MAX[St – X, 0]e-rt
5. Average
AVERAGE
CONVERGENCE
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492500.0
2.0
4.0
6.0
8.0
10.0
12.0
14.0
16.0
18.0
Option Value for Increasing Number of Runs
Number of Runs
Op
tio
n V
alu
e
VERIFICATION AND VALIDATIONVerification –Whether software correctly implements specified model
Validation –Whether the simulation model (perfectly coded) is acceptable representation
ADVANCED TECHNIQUES
Antithetic Variables
Control Variate Technique
Quasi-Random Sequences