Chapter 5

Statistical Models in
Simulation

Banks, Carson, Nelson & Nicol

Discrete-Event System Simulation

Purpose & Overview

„ The world the model-builder sees is probabilistic rather
than deterministic.
Some statistical model might well describe the variations.

„ An appropriate model can be developed by sampling the

phenomenon of interest:
Select a known distribution through educated guesses
Make estimate of the parameter(s)
Test for goodness of fit

„ In this chapter:
Review several important probability distributions
Present some typical application of these models

١
Review of Terminology and Concepts

„ In this section, we will review the following

concepts:
Discrete random variables
Continuous random variables
Cumulative distribution function
Expectation

Discrete Random Variables [Probability Review]

„ X is a discrete random variable if the number of possible

values of X is finite, or countably infinite.
„ Example: Consider jobs arriving at a job shop.
„ Let X be the number of jobs arriving each week at a job shop.
„ Rx = possible values of X (range space of X) = {0,1,2,…}
„ p(xi) = probability the random variable is xi = P(X = xi)
p(xi), i = 1,2, … must satisfy:
1. p ( xi ) ≥ 0, for all i

∑
∞
2. i =1
p ( xi ) = 1

The collection of pairs [xi, p(xi)], i = 1,2,…, is called the probability

distribution of X, and p(xi) is called the probability mass function
(pmf) of X.

٢
Continuous Random Variables [Probability Review]

„ X is a continuous random variable if its range space Rx is an interval

or a collection of intervals.
„ The probability that X lies in the interval [a,b] is given by:
b
P(a ≤ X ≤ b) = ∫ f ( x)dx
a

„ f(x), denoted as the pdf of X, satisfies:

1. f ( x) ≥ 0 , for all x in R X
2. ∫ f ( x)dx = 1
RX

3. f ( x) = 0, if x is not in RX
„ Properties
x0
1. P( X = x0 ) = 0, because ∫ f ( x)dx = 0
x0

2. P(a ≤ X ≤ b) = P( a p X ≤ b) = P( a ≤ X p b) = P (a p X p b)

Continuous Random Variables [Probability Review]

„ Example: Life of an inspection device is given by X, a

continuous random variable with pdf:

1 −x / 2
 e , x≥0
f ( x) =  2
0, otherwise

X has an exponential distribution with mean 2 years

Probability that the device’s life is between 2 and 3 years is:
1 3 −x/ 2
2 ∫2
P(2 ≤ x ≤ 3) = e dx = 0.14

٣
Cumulative Distribution Function [Probability Review]

„ Cumulative Distribution Function (cdf) is denoted by F(x), where F(x)

= P(X <= x)
If X is discrete, then F ( x) = ∑ p ( xi )
all
xi ≤ x
If X is continuous, then x
F ( x) = ∫ f (t )dt
−∞

„ Properties
1. F is nondecreasing function. If a p b, then F ( a) ≤ F (b)
2. lim x→∞ F ( x) = 1
3. lim x→ −∞ F ( x ) = 0

„ All probability question about X can be answered in terms of the cdf,

e.g.:
P( a p X ≤ b) = F (b) − F (a ), for all a p b

Cumulative Distribution Function [Probability Review]

„ Example: An inspection device has cdf:

1 x −t / 2
2 ∫0
F ( x) = e dt = 1 − e − x / 2

The probability that the device lasts for less than 2 years:
P (0 ≤ X ≤ 2) = F (2) − F (0) = F ( 2) = 1 − e −1 = 0.632

The probability that it lasts between 2 and 3 years:

P( 2 ≤ X ≤ 3) = F (3) − F (2) = (1 − e − (3 / 2 ) ) − (1 − e −1 ) = 0.145

٤
Expectation [Probability Review]

„ The expected value of X is denoted by E(X)

If X is discrete E ( x) = ∑ xi p ( xi )
all i
∞
If X is continuous E ( x) = ∫ xf ( x)dx
−∞

a.k.a the mean, m, or the 1st moment of X

A measure of the central tendency
„ The variance of X is denoted by V(X) or var(X) or σ2
Definition: V(X) = E[(X – E[X]2]
Also, V(X) = E(X2) – [E(x)]2
A measure of the spread or variation of the possible values of X around
the mean
„ The standard deviation of X is denoted by σ
B10square root of V(X)
Definition:
Expressed in the same units as the mean

Expectations [Probability Review]

„ Example: The mean of life of the previous inspection device

is: ∞
1 ∞ −x / 2 −x / 2
xe dx = − xe
∞
E( X ) =
2 ∫0
0
+ ∫ e − x / 2 dx = 2
0

„ To compute variance of X, we first compute E(X2):

∞
1 ∞ −x / 2
E ( X ) = ∫ x 2 e − x / 2 dx = − x 2 e
∞
2
+ ∫ e − x / 2 dx = 8
2 0 0
0

„ Hence, the variance and standard deviation of the device’s life

are:
V (X ) = 8 − 2 = 4
2

σ = V (X ) = 2
١٠

٥
Slide 9

B10 after :, two spaces, then next word starts with a capital letter
Brian; 2005/01/07
Useful Statistical Models

„ In this section, statistical models appropriate to

some application areas are presented. The
areas include:
Queueing systems
Inventory and supply-chain systems
Reliability and maintainability
Limited data

١١

Queueing Systems [Useful Models]

„ In a queueing system, interarrival and service-time

patterns can be probablistic (for more queueing examples, see
Chapter 2).
„ Sample statistical models for interarrival or service time
distribution:
Exponential distribution: if service times are completely random
Normal distribution: fairly constant but with some random
variability (either positive or negative)
Truncated normal distribution: similar to normal distribution but
with restricted value.
Gamma and Weibull distribution: more general than exponential
(involving location of the modes of pdf’s and the shapes of tails.)

١٢

٦
Inventory and supply chain [Useful Models]

„ In realistic inventory and supply-chain systems, there are

at least three random variables:
The number of units demanded per order or per time period
The time between demands
The lead time
„ Sample statistical models for lead time distribution:
Gamma
„ Sample statistical models for demand distribution:
Poisson: simple and extensively tabulated.
Negative binomial distribution: longer tail than Poisson (more
large demands).
Geometric: special case of negative binomial given at least one
demand has occurred.

١٣

Reliability and maintainability [Useful Models]

„ Time to failure (TTF)

Exponential: failures are random
Gamma: for standby redundancy where each
component has an exponential TTF
Weibull: failure is due to the most serious of a large
number of defects in a system of components
Normal: failures are due to wear

١٤

٧
Other areas [Useful Models]

„ For cases with limited data, some useful

distributions are:
Uniform, triangular and beta
„ Other distribution: Bernoulli, binomial and
hyperexponential.

١٥

Discrete Distributions

„ Discrete random variables are used to describe

random phenomena in which only integer values
can occur.
„ In this section, we will learn about:
Bernoulli trials and Bernoulli distribution
Binomial distribution
Geometric and negative binomial distribution
Poisson distribution

١٦

٨
Bernoulli Trials
and Bernoulli Distribution [Discrete Dist’n]
„ Bernoulli Trials:
Consider an experiment consisting of n trials, each can be a
success or a failure.
„ Let Xj = 1 if the jth experiment is a success
„ and Xj = 0 if the jth experiment is a failure
The Bernoulli distribution (one trial):
 p, x j = 1, j = 1,2,..., n

p j ( x j ) = p( x j ) = 1 − p = q, x j = 0,j = 1,2,...,n
0, otherwise

where E(Xj) = p and V(Xj) = p(1-p) = pq
„ Bernoulli process:
The n Bernoulli trials where trails are independent:
p(x1,x2,…, xn) = p1(x1)p2(x2) … pn(xn)

١٧

Binomial Distribution [Discrete Dist’n]

„ The number of successes in n Bernoulli trials, X, has a

binomial distribution.
 n  x n − x
  p q , x = 0,1,2,..., n
p( x) =  x 
0, otherwise

The number of
Probability that
outcomes having the
there are
required number of
x successes and
successes and
(n-x) failures
failures

The mean, E(x) = p + p + … + p = n*p

The variance, V(X) = pq + pq + … + pq = n*pq

١٨

٩
Geometric & Negative
Binomial Distribution [Discrete Dist’n]

„ Geometric distribution
The number of Bernoulli trials, X, to achieve the 1st success:
 q x −1 p, x = 0,1,2,..., n
p( x) = 
0, otherwise
E(x) = 1/p, and V(X) = q/p2

„ Negative binomial distribution

The number of Bernoulli trials, X, until the kth success
If Y is a negative binomial distribution with parameters p and k,
then:
 y − 1 y − k k
  q p , y = k , k + 1, k + 2,...
p ( x) =  k − 1
0, otherwise

E(Y) = k/p, and V(X) = kq/p 2

١٩

Poisson Distribution [Discrete Dist’n]

„ Poisson distribution describes many random processes

quite well and is mathematically quite simple.
where α > 0, pdf and cdf are:
 e −α α x x
e −α α i

p ( x) =  x! , x = 0,1,... F ( x) = ∑
i =0 i!
0, otherwise

E(X) = α = V(X)

٢٠

١٠
Poisson Distribution [Discrete Dist’n]

„ Example: A computer repair person is “beeped” each

time there is a call for service. The number of beeps per
hour ~ Poisson(α = 2 per hour).

The probability of three beeps in the next hour:

p(3) = e-223/3! = 0.18
also, p(3) = F(3) – F(2) = 0.857-0.677=0.18

The probability of two or more beeps in a 1-hour period:

p(2 or more) = 1 – p(0) – p(1)
= 1 – F(1)
= 0.594

٢١

Continuous Distributions

„ Continuous random variables can be used to

describe random phenomena in which the
variable can take on any value in some interval.
„ In this section, the distributions studied are:
Uniform
Exponential
Normal
Weibull
Lognormal

٢٢

١١
Uniform Distribution [Continuous Dist’n]

„ A random variable X is uniformly distributed on the

interval (a,b), U(a,b), if its pdf and cdf are:
 1 0, xpa
 , a≤ x≤b x −a
f ( x) =  b − a F ( x) =  , a≤ xpb
0, otherwise b − a
1, x≥b

„ Properties
P(x1 < X < x2) is proportional to the length of the interval [F(x2) –
F(x1) = (x2-x1)/(b-a)]
E(X) = (a+b)/2 V(X) = (b-a)2/12
„ U(0,1) provides the means to generate random numbers,
from which random variates can be generated.

٢٣

Exponential Distribution [Continuous Dist’n]

„ A random variable X is exponentially distributed with

parameter λ > 0 if its pdf and cdf are:
λe − λx , x ≥ 0 0, xp0
f ( x) =  F ( x ) =  x − λt
∫0
− λx
0, elsewhere λ e dt = 1 − e , x≥0

E(X) = 1/λ V(X) = 1/λ2

Used to model interarrival times
when arrivals are completely
random, and to model service
times that are highly variable
For several different exponential
pdf’s (see figure), the value of
intercept on the vertical axis is λ,
and all pdf’s eventually intersect.
٢٤

١٢
Exponential Distribution [Continuous Dist’n]

„ Memoryless property
For all s and t greater or equal to 0:
P(X > s+t | X > s) = P(X > t)

Example: A lamp ~ exp(λ = 1/3 per hour), hence, on

average, 1 failure per 3 hours.
„ The probability that the lamp lasts longer than its mean life is:
P(X > 3) = 1-(1-e-3/3) = e-1 = 0.368
„ The probability that the lamp lasts between 2 to 3 hours is:
P(2 <= X <= 3) = F(3) – F(2) = 0.145
„ The probability that it lasts for another hour given it is
operating for 2.5 hours:
P(X > 3.5 | X > 2.5) = P(X > 1) = e-1/3 = 0.717

٢٥

Normal Distribution [Continuous Dist’n]

„ A random variable X is normally distributed has the pdf:

1  1  x − µ 2 
f ( x) = exp −   , − ∞ p x p ∞
σ 2π  2  σ  

Mean: −∞ p µ p ∞
Variance: σ 2 f 0
Denoted as X ~ N(µ,σ2)
„ Special properties:
lim x →−∞ f ( x) = 0, and lim x→∞ f ( x) = 0.
f(µ-x)=f(µ+x); the pdf is symmetric about µ.
The maximum value of the pdf occurs at x = µ; the mean and
mode are equal.

٢٦

١٣
Normal Distribution [Continuous Dist’n]

„ Evaluating the distribution:

Use numerical methods (no closed form)
Independent of µ and σ, using the standard normal distribution:
Z ~ N(0,1)
Transformation of variables: let Z = (X - µ) / σ,
 x−µ 
F ( x ) = P ( X ≤ x ) = P Z ≤ 
 σ 
( x−µ ) /σ 1 −z2 / 2
=∫ e dz
−∞
2π
( x−µ ) /σ
=∫ φ ( z )dz = Φ( xσ− µ ) , where Φ ( z ) = ∫
z 1 −t 2 / 2
e dt
−∞ −∞
2π

٢٧

Normal Distribution [Continuous Dist’n]

„ Example: The time required to load an oceangoing

vessel, X, is distributed as N(12,4)
The probability that the vessel is loaded in less than 10 hours:
 10 − 12 
F (10) = Φ  = Φ (−1) = 0.1587
 2 
„ Using the symmetry property, Φ(1) is the complement of Φ (-1)

٢٨

١٤
Weibull Distribution [Continuous Dist’n]

„ A random variable X has a Weibull distribution if its pdf has the form:
 β  x −ν  β −1   x −ν  β 
 
f ( x) = α  α   exp −   , x ≥ ν
  α  
0, otherwise

„ 3 parameters:
Location parameter: υ, (−∞ p ν p ∞)
Scale parameter: β , (β > 0)
Shape parameter. α, (> 0)
„ Example: υ = 0 and α = 1:

When β = 1,
X ~ exp(λ = 1/α)

٢٩

Lognormal Distribution [Continuous Dist’n]

„ A random variable X has a lognormal distribution if its

pdf has the form:
 1  (ln x − µ ) 2  µ=1,
 exp − , x f 0
f ( x) =  2π σx 2σ 2 σ2=0.5,1,2.
 
0, otherwise

2
Mean E(X) = eµ+σ /2
2 2
Variance V(X) = e2µ+σ /2 (eσ - 1)

„ Relationship with normal distribution

When Y ~ N(µ, σ2), then X = eY ~ lognormal(µ, σ2)
Parameters µ and σ2 are not the mean and variance of the
lognormal
٣٠

١٥
Poisson Distribution
„ Definition: N(t) is a counting function that represents
the number of events occurred in [0,t].
„ A counting process {N(t), t>=0} is a Poisson process
with mean rate λ if:
Arrivals occur one at a time
{N(t), t>=0} has stationary increments
{N(t), t>=0} has independent increments
„ Properties
e − λt ( λt ) n
P[ N (t ) = n] = , for t ≥ 0 and n = 0,1,2,...
n!

Equal mean and variance: E[N(t)] = V[N(t)] = λt

Stationary increment: The number of arrivals in time s to t is
also Poisson-distributed with mean λ(t-s)

٣١

Interarrival Times [Poisson Dist’n]

„ Consider the interarrival times of a Possion process (A1, A2, …),

where Ai is the elapsed time between arrival i and arrival i+1

The 1st arrival occurs after time t iff there are no arrivals in the interval
[0,t], hence:
P{A1 > t} = P{N(t) = 0} = e-λt
P{A1 <= t} = 1 – e-λt [cdf of exp(λ)]
Interarrival times, A1, A2, …, are exponentially distributed and
independent with mean 1/λ

Arrival counts Interarrival time

Poi(λ)
~ B42 ~ Exp(1/λ)
Stationary & Independent Memoryless

٣٢

١٦
Slide 32

B42 Poi is not an abbreviation of Poisson that I have ever seen

Brian; 2005/01/07
Splitting and Pooling [Poisson Dist’n]

„ Splitting:
Suppose each event of a Poisson process can be classified as
Type I, with probability p and Type II, with probability 1-p.
N(t) = N1(t) + N2(t), where N1(t) and N2(t) are both Poisson
processes with rates λ p and λ (1-p)
λp N1(t) ~ Poi[λp]
N(t) ~ Poi(λ) λ

λ(1-p) N2(t) ~ Poi[λ(1-p)]

„ Pooling:
Suppose two Poisson processes are pooled together
N1(t) + N2(t) = N(t), where N(t) is a Poisson processes with rates
λ1 + λ2 λ
N1(t) ~ Poi[λ1] 1
λ1 + λ2
N(t) ~ Poi(λ1 + λ2)
N2(t) ~ Poi[λ2] λ2
٣٣

Nonstationary Poisson
Process (NSPP) [Poisson Dist’n]
„ Poisson Process without the stationary increments, characterized by
λ(t), the arrival rate at time t.
„ The expected number of arrivals by time t, Λ(t):
t
Λ(t) = ∫ λ(s)ds
0

„ Relating stationary Poisson process n(t) with rate λ=1 and NSPP N(t)
with rate λ(t):
Let arrival times of a stationary process with rate λ = 1 be t1, t2, …,
and arrival times of a NSPP with rate λ(t) be T1, T2, …, we know:
ti = Λ(Ti)
Ti = Λ−1(ti)

٣٤

١٧
Nonstationary Poisson
Process (NSPP) [Poisson Dist’n]
„ Example: Suppose arrivals to a Post Office have rates 2 per minute
from 8 am until 12 pm, and then 0.5 per minute until 4 pm.
„ Let t = 0 correspond to 8 am, NSPP N(t) has rate function:
2, 0 ≤ t p 4
λ (t ) = 
0.5, 4 ≤ t p 8
Expected number of arrivals by time t:
2t , 0≤t p4
Λ (t ) =  4 t t
∫0 2ds + ∫4 0.5ds = 2 + 6, 4 ≤ t p 8
„ Hence, the probability distribution of the number of arrivals between
11 am and 2 pm.
P[N(6) – N(3) = k] = P[N(Λ(6)) – N(Λ(3)) = k]
= P[N(9) – N(6) = k]
= e(9-6)(9-6)k/k! = e3(3)k/k!

٣٥

Empirical Distributions [Poisson Dist’n]

„ A distribution whose parameters are the observed values

in a sample of data.
May be used when it is impossible or unnecessary to establish that
a random variable has any particular parametric distribution.
Advantage: no assumption beyond the observed values in the
sample.
Disadvantage: sample might not cover the entire range of possible
values.

٣٦

١٨
Summary
„ The world that the simulation analyst sees is probabilistic,
not deterministic.
„ In this chapter:
Reviewed several important probability distributions.
Showed applications of the probability distributions in a simulation
context.
„ Important task in simulation modeling is the collection and
analysis of input data, e.g., hypothesize a distributional
form for the input data. Reader should know:
Difference between discrete, continuous, and empirical
distributions.
Poisson process and its properties.

٣٧

١٩