Transcript Models

.
Analysis of
Simulation Input
Simulation Machine

Simulation can be considered as an Engine
with input and output as follows:
Input
Simulation
Engine
Output
Realizing Simulation

Input Analysis: is the analysis of the random
variables involved in the model such as:
 The
distribution of IAT
 The distribution of Service Times

Simulation Engine is the way of realizing the model,
this includes:
 Generating
Random variables involved in the model
 Performing the required formulas.

Output Analysis is the study of the data that are
produced by the Simulation engine.
Input Analysis



collect data from the field
Analyze these data
Two ways to analyze the data:
 Build
Empirical distribution and then sample from this
distribution.
 Fit the data to a theoretical distribution ( such as
Normal, Exponential, etc.) See Chapter 3 of Text for
more distributions.
Empirical Distributions

Consider the following 30-data numerical
example
Example Continue

We might take these data and construct an
empirical distribution by developing a histogram
Frequency
More
Disadvantages of
Empirical distribution



The empirical data may not adequately represent
the true underlying population because of sampling
error
The Generated RV’s are bounded
To overcome these two problems, we attempt to fit
a theoretical distribution.
Fitting a Theoretical
Distribution


Need a good background of the
theoretical distributions. Histogram is
useful but may not provide much insight
into the nature of the distribution.
Need Summary statistics: Use Data
Analysis that Microsoft Excel can do.
Summary Statistics





Mean
Median
Standard Deviation(SD)
Coefficient of Variation (SD divided by
the Mean)
Skewness index
Summary Stats. Cont.



If the Mean and the Median are close to each
others, and low Coefficient of Variation, we
would expect a Normally distributed data.
If the Median is less than the Mean, and SD is
very close to the Mean, we expect an
exponential distribution.
If the skewness is very low then the data are
symmetric.
Example Cont.
Use Data Analysis of Microsoft Excel
 Mean
5.654198
 Median
5.486928
 Standard Deviation
0.910188
 Skewness
0.173392
 Range
3.475434
 Minimum 4.132489
 Maximum
7.607923
The given summary statistics suggest a
Normal Distribution
Hypothesizing a
Theoretical Distribution

Use the Summary statistics to hypothesize a
family of distributions.
MLE





Use the Maximum Likelihood Estimator (MLE) to
estimate the parameters involved with the
hypothesized distribution.
Suppose that q is the parameter involve in the
distribution then construct
Let L(q) = fq (X1) fq (X2) . . . fq(Xn)
Find q that maximize L(q) to be the required parameter.
Example: the exponential distribution.
Goodness of Fit (Chi
Square method)

Determine how well the given distribution is
representing the data.
1.
2.
3.
Divide the range of the fitted distribution into k
intervals [a0, a1), [a1, a2), … [ak-1, ak] Let Nj = the
number of data that belong to [aj-1, aj)
Compute the expected proportion of the data that
fall in the jth interval using the fitted distribution
call them pj
k ( N  np ) 2
Compute the Chi-square
j
j
2
 =
j =1
np j
Chi-square cont.


Note that npj represents the expected number of
data that would fall in the jth interval if the fitted
distribution is correct.
If
   k 1,1a
2

2
Then accept the distribution with significance (1a)100%.