2008 Winton

1
Distributions
2008 Winton
2
Recap
An integrable function f : R [0,1] such that Rf(x)dx = 1 is
called a probability density function (pdf)
The distribution function for the pdf is given by
and corresponds to the cumulative distribution function for the
discrete case
Sampling from the distribution corresponds to solving the equation
for rsample given random probability values 0 x 1

=
x
-
f(z)dz F(x)

=
rsample
-
f(z)dz x
2008 Winton
3
Uniform Distribution
The pdf for values uniformly distributed across [a,b] is given by
f(x) =
rsample
probability density function
(area under the curve = 1)
p(x)
1
(b-a)
1
(b-a)
2008 Winton
4
Sampling from the Uniform
Distribution
(pseudo)random numbers x drawn from [0,1] distribute uniformly
across the unit interval, so it is evident that the corresponding values
rsample = a + x(b-a)
will distribute uniformly across [a,b]
Directly solving
for rsample as per
also yields rsample = a + x(b-a) (exactly as it should!)

=
rsample
-
f(z)dz x

a - b
a
-
a - b a - b
z
dz
a - b
1
x
a
a
rsample
rsample
rsample
=

= =

0
1
b
a
rsample
x
slope = (b-a)
2008 Winton
5
Mean and Variance for the Uniform
Distribution
The mean of the uniform distribution is given by
The standard deviation of the uniform distribution is obtained from the
variance
2
where
2
a b
a - b
1
2
a b
dz
a - b
1
z E(X)
2 2
b
a
+
=

= =

(midpoint of [a, b] )
z f(z) dz
12
a) - (b
dz
a - b
1
2
a b
- z ) ) - E((X
2
2
b
a
2 2
=

+
= =

(with some work)
(z-)
2
f(z) dz
2008 Winton
6
Normal Distribution
For a finite population the mean (m) and standard deviation (s)
provide a measure of average value and degree of variation from the
average value
If random samples of size n are drawn from the population, then it
can be shown (the Central Limit Theorem) that the distribution of the
sample means approximates that of a distribution with
mean: = m and .
standard deviation:
pdf:
which is called the Normal Distribution
The pdf is characterized by its "bell-shaped" curve, typical of
phenomena that distribute symmetrically around the mean value in
decreasing quantity as one moves away from the mean
n
s
=
2
2
2
) (x
e
2
1
f(x)

=
2008 Winton
7
Empirical Rule for Normal
Distribution
The "empirical rule" is that
approximately 68% of sample values are in the interval [-,+]
approximately 95% are in the interval [-2,+2]
almost all are in the interval [-3,+3]
This says that if n is large enough, then a sample mean for
the population is accurate with a high degree of
confidence, since decreases with n
What constitutes "large enough" is largely a function of the
underlying population distribution
The Central Limit Theorem assumes that the samples of size n
which are used to produce sample means are drawn in a random
fashion
2008 Winton
8
Measurements Found to Distribute
Normally
Hogg and Craig (Introduction to Mathematical Statistics) cites as distributing normally
such disparate phenomena as
The diameter of the hole made by a drill press
The score on a test
The yield of grain for a plot of ground
The length of a newborn child
The assumption that grades on a test distribute normally is the basis for so-called
"curving" of grades
This assumes some underlying random phenomena controls the measure given by a test
e.g., genetic selection
The practice sometimes is used to assign grades of A,B,C,D,F based on how many
"standard deviations" separates a percentile score from the mean
If the mean score is 77.5, and the standard deviation is 8, then the curve of the class scores
would be given by
A: 94 and up (2.5%)
B: 86-93 (13.5%)
C: 70-85 (68%)
D: 62-69 (13.5%)
F: otherwise (2.5%)
Most people "pass", but A's are hard to get
This could be pretty distressing if the mean is 95 and the standard deviation is 2 (i.e., 90 is an F)
2008 Winton
9
Normal Distribution: Example Plot
Plot with with = 30 and = 10
The distribution is completely determined by knowing the value of and
x
f(x)

2008 Winton
10
2
x
2
e
2
1
f(x)

=
dz e
2
1

2
z
2

=
nsample
x
nsample
Standard Normal Distribution
The standard normal distribution is given by = 0 and = 1, in which case the
pdf becomes
2008 Winton
11
Sampling from the Normal
Distribution
The linear relationship
rsample = + nsample
between a normal distribution and
the standard normal distribution
means it is sufficient to sample
from the standard normal
distribution
There is no "closed-form formula"
for nsample, so approximation
techniques for inverting the
cumulative distribution function or
a method such as accept-reject has
to be used
.5 1
0
nsample
x
dt e
2
1
dt e
2
1
dz e
2
1
2
) t (

-
2
) - t (
-
2
) - (z
-
2
2
2
2

+ +

= =

nsample nsample rsample
substitute z=+t
dz = dt
2008 Winton
12
Exponential Distribution
The exponential distribution arises in connection with Poisson
processes
A Poisson process is one exhibiting a random arrival pattern in the
following sense:
For a small time interval t, the probability of an arrival during t is t,
where = the mean arrival rate
The probability of more than one arrival during t is negligible
Interarrival times are independent of each other.
This is a kind of "stochastic" process, one for which events occur in a
random fashion
Under these assumptions, it can be shown that the pdf for the
distribution of interarrival times is given by
which is the exponential distribution
x -
e f(x) =
2008 Winton
13
Properties of the Exponential
Distribution
If it can be shown that the number of arrivals during an interval is
Poisson distributed (i.e., the arrival times are Poisson distributed), then
the interarrival times are exponentially distributed
The mean arrival rate is given by and the mean interarrival time is given
by 1/
The Poisson distribution is a discrete distribution closely related to the
binomial distribution and will be considered later
It can be shown for the exponential distribution that the mean is equal
to the standard deviation; i.e.,
= = 1/
The exponential distribution is the only continuous distribution that is
"memoryless", in the sense that P(X > a+b | X > a) = P(X > b)
2008 Winton
14
Graphical Appearance of the
Exponential Distribution

x
f(x)
rsample
x -
e f(x)=
2008 Winton
15
Standard Exponential Distribution
The case = 1 gives the standard exponential
distribution
Inverting is straight forward since
closed form formula for obtaining a normalized sample
value (nsample) using a random probability x
General sample values (rsample) are obtained
from the standard exponential distribution by
x e - 1 e - dz e
0
z -
0
z
= = =

-nsample
nsample
nsample
so nsample = -log
e
(1-x)
x) - (1 log

1
-

1

e
= = nsample rsample
2008 Winton
16
Sampling Function for the Standard
Exponential Distribution
1/
(e-1)/e
rsample
0 1
x
x) - (1 log

1
-
e
2008 Winton
17
Considerations in Using the
Exponential Distribution
The utility of the exponential distribution for discrete systems
simulation is its effectiveness for modeling a random arrival pattern
Implicit characteristic of a Poisson process
Sampling for interarrival times is a natural approach for introducing new
items into the model one at a time
Care must be taken that when used for this purpose, the exponential
distribution is applied to relatively short time periods during which the
arrival rate is not dependent on time of day
For example, the model could progress in 1 hour service intervals representing
slow, moderate, and peak demand, each governed by an exponential
distribution with an appropriate mean interarrival time
A more sophisticated approach is to adjust the arrival rates
dynamically with time, a concept studied under the topic of joint
probability distributions
2008 Winton
18
Verfication that = for the
Exponential Distribution
For the pdf of the exponential distribution note that
f(x) = -
2
e
- x
so f(0) = and f(0) = -
2
Hence, if < 1 the curve starts lower and flatter than for the standard
exponential. The asymptotic limit is the x-axis.

1
e

1 -
0 dz e ze - dz e z E(X)
0
x
0
z -
0
z -
0
z -
= + = + = = =

vdu uv -
( ) ( ) ( ) ( ) ( )dz 1/ - z 2 e - - e 1/ - z - dz e 1/ - z 1/ - X E
0
z -
0
z -
2
z -
0
2 2
2

= = =
2
0
z
2
0
z
2

1
dz e

2
- dz e z

1
= + =

u dv
(integration by parts)
u dv
x -
e f(x) =
= 1/
= 1 (by definition)