Random

variables
Probability distributions of a
Discrete Random Variable
 Consider the following random experiments and
random variables:
1. Flip a coin 10 times. Let X = number of heads
obtained
2. A worn machine tool produces 1% defective parts.
Let X = number of defective parts in the next
25 parts produced
3. Each sample of air has a 10% chance of containing a
particular rare molecule. Let X = the number of air
samples that contain the rare molecule in the next
18 samples analyzed
4. Of all bits transmitted through a digital transmission
channel, 10% are received in error. Let X = the
number of bits in error in the next five bits
transmitted
1. A multiple choice test contains 10 questions, each with
four choices, and you guess at each question. Let X =
the number of questions answered correctly
2. 6. In the next 20 births at a hospital, let X = the
number of female births
3. 7. Of all patients suffering a particular illness, 35%
experience improvement from a particular medication.
In the next 100 patients administered the medication,
let X = the number of patients who experience
improvement.
 Each of these random experiments can be
thought of as consisting of a series of repeated,
random trials: 10 flips of the coin in experiment
1, the production of 25 parts in experiment 2,
and so forth
 Each trial can be summarized as resulting in either a
success or a failure
 A trial with only two possible outcomes is
used so frequently as a building block of a
random experiment that it is called a
Bernoulli trial
 It is usually assumed that the trials that
constitute the random experiment are
independent
 the outcome from one trial has no effect on
the outcome to be obtained from any other trial
 Furthermore, it is often reasonable to
assume that the probability of a success
in each trial is constant
 A random experiment consists of n Bernoulli trials
such that
1. The trials are independent
2. Each trial results in only two possible outcomes, labeled
as “success’’ and “failure’’
3. The probability of a success in each trial, denoted as p,
remains constant
 The random variable X that equals the number of
trials that result in a success has a binomial random
variable with parameters 0 < p < 1 and n = 1, 2,…
 The probability mass function of X is

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 The chance that a bit transmitted through a digital
transmission channel is received in error is 0.1
 Also, assume that the transmission trials are independent
 Let X = the number of bits in error in the next four bits
transmitted. Determine (X = 2)
 Let the letter E denote a bit in error, and
 Let the letter O denote that the bit is received without
error

OEOE indicates that the second and fourth

bits are in error and the other two bits are
okay

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 The event that X = 2 consists of the six outcomes:
{ EEOO, EOEO, EOOE, OEEO, OEOE, OOEE }
 Using the assumption that the trials are independent,
P(EEOO) = P(E)P(E)P(O)P(O) = (0.1)2(0.9)2 = 0.0081
 Also, any one of the six mutually exclusive outcomes for which
X = 2 has the same probability of occurring. Therefore,
P(X = 2) = 6(0.0081) = 0.0486
 In general,
P(X = x) = (no. of outcomes of x errors) times (0.1)x(0.9)4-x

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  An outcome that contains x errors can be
constructed by partitioning the four trials
(letters) in the outcome into two groups.
 One group is of size x and contains the errors,
and
 the other group is of size n - x and consists of
the trials that are okay
 The number of ways of partitioning four
objects into two groups, one of which
Example is of
x=2
size x, is

 Therefore, P(X = 2) = 6× (0.1)2(0.9)2 = 6 * 0.0081 = 0.0486

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 BIONOMIAL
DISTRIBUTIONS
EXAMPLES

Binomial distributions for selected values of n and p

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 BIONOMIAL EXPANSION

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 BIONOMIAL
DISTRIBUTIONS
MEAN AND VARIANCE
 If X is a binomial random variable with
parameters p and n
μ = E(X) = np and σ2 = V(X) = np(1 - p)

 Example
 For the number of transmitted bits received in
error in the last example, n = 4 & p = 0.1 so
μ = E(X) = 4(0.1) = 0.4 and
σ2 = V(X) = 4(0.1)(0.9) = 0.36

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC RANDOM
VARIABLE
 In a series of Bernoulli trials (independent
trials with constant probability p of a success),
 let the random variable (rv) X denote the
number of trials until the first success
 Then X is a geometric random variable with
parameter 0 < p < 1 and

f(x) = (1 - p)x-1p , x = 1, 2

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC DISTRIBUTION
EXAMPLE
 The probability that a bit transmitted through a
digital transmission channel is received in error is
0.1
 If it is assumed that the transmissions are
independent, what is the probability that the first
four bits are transmitted correctly and the fifth bit is
in error?
 Let X denote the number of bits transmitted until
the first error , then P(X = 5) = ?
 Then X is a geometric random variable with p = 0.1
 The requested probability is
P(X = 5) = P(OOOOE) = (0.9)4(0.1) = 0.0066

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC DISTRIBUTION
EXAMPLE 2
 The probability that a wafer contains a large
particle of contamination is 0.01
 If it is assumed that the wafers are
independent, what is the probability that exactly
125 wafers need to be analyzed before a large
particle is detected?
 Let X denote the number of samples analyzed
until a large particle is detected
 Then X is a geometric random variable with p =
0.01
 The requested probability is
P(X = 125) = (0.99)124(0.01) = 0.0029

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC DISTRIBUTION
EXAMPLE
 Note that the height of
the line at x is (1- p)
times the height of the
line at x - 1
Geometric distributions
 That is, the
for selected values of n and p
probabilities decrease
in a geometric
progression

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC
DISTRIBUTION
MEAN AND VARIANCE
 If X is a geometric random variable with
parameters p and n
μ = E(X) = 1/p and σ2 = V(X) = (1 - p)/p2

 Example
For the number of transmitted bits received in
error in the last example, p = 0.1 so
μ = E(X) = 1/0.1 = 10
= mean number of transmissions until the
first error
σ = V√(X) = [(1 - 0.1)/(0.1)2]1/2 = 9.49
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 GEOMETRIC
DISTRIBUTION
LACK OF MEMORY PROPERTY
 A geometric random variable has been defined as the
number of trials until the first success
 However, because the trials are independent, the
count of the number of trials until the next success
can be started at any trial without changing the
probability distribution of the random Variable
 For example, in the transmission of bits, if 100 bits are
transmitted, the probability that the first error, after
bit 100, occurs on bit 106 is the probability that the
next six outcomes are OOOOOE = (0.9)5(0.1) =
0.059
= the probability that the initial error occurs on bit 6
 the geometric distribution is said to
lack any memory
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
NEGATIVE BINOMIAL
DISTRIBUTION
 A generalization of a geometric distribution in
which the random variable is the number of
Bernoulli trials required to obtain r successes
results in the negative binomial
distribution.
 Definition
In a series of Bernoulli trials (independent trials
with constant probability p of a success),
 let the random variable X denote the number of
trials until r successes occur
 Then X is a negative binomial random
variable with parameters 0 < p < 1 and r = 1,
2 3,…, and
 NEGATIVE BINOMIAL
DISTRIBUTION EXAMPLES

Negative Binomial distributions for selected values of n and p

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 NEGATIVE BIONOMIAL
DISTRIBUTION
LACK OF MEMORY PROPERTY
 Let X denote the total number of trials required to obtain r
successes. Let
 X1 = number of trials required to obtain the first success,
 X2 = number of extra trials required to
 obtain the second success,
 X3 = number of extra trials to obtain the third success

…
 The total number of trials required to obtain r successes

= X = X1 + X2 + … + Xr
 The lack of memory property  each of the rv has a
geometric distribution with the same value of p
 Consequently, a negative binomial random variable can
be interpreted as the sum of r geometric random variables
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
DISTRIBUTION
EXAMPLE
 The probability of a single bit transmisssion is 0.1
 If it is assumed that the transmissions are independent, Let
X denote the number of bits transmitted until the fourth error
 Then, X has a negative binomial distribution with r = 4
Probabilities involving X can be found as follows
 The P(X = 10) is the probability that exactly three errors
occur in the first nine trials and then trial 10 results in the
fourth error
 The probability that exactly three errors occur in the first nine
trials is determined from the binomial distribution to be

 Trials are independent  the probability that exactly three

errors occur in the first 9 trials and trial 10 results in the
fourth error is the product of the probabilities of these two
events, namely
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
DISTRIBUTION
EXAMPLE
 The probability of a single bit transmission is 0.1
 If it is assumed that the transmissions are independent, Let
X denote the number of bits transmitted until the fourth
error
 Then, X has a negative binomial distribution with r = 4
Probabilities involving X can also be found as follows
 x  1 x r r
  (1  p ) p
 r  1
 10  1 10  4 4  9 6 4
  (1  0.1) (0.1)    (0.9) (0.1)
 4  1   3
9! 9.8.7
 (0.0005)  (0.0005) (84)(0.0005) 0.0042
6!3! 3.2.1

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 NEGATIVE BIONOMIAL
DISTRIBUTION
MEAN AND VARIANCE
 If X is a negative binomial random variable with
parameters p and r
μ = E(X) = r/p and σ2 = V(X) = r(1 - p)/p2

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
NEGATIVE BIONOMIAL
DISTRIBUTION
EXAMPLE
 A web site contains three identical computer
servers
 Only one is used to operate the site, and the
other two are spares that can be activated in
case the primary system fails.
 The probability of a failure in the primary
computer (or any activated spare system) from a
request for service is 0.0005.
 Assuming that each request represents an
independent trial, what is the mean number of
requests until failure of all three servers?

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
NEGATIVE BIONOMIAL
DISTRIBUTION
EXAMPLE
 what is the mean number of requests until failure of
all three servers?
 Let X denote the number of requests until all three
servers fail, and
 let , X1, X2 and X3, denote the number of requests
before a failure of the first, second, and third servers
used, respectively
X = X 1 + X2 + X3
 A spare server is not affected by the number of
requests before it is activated
 Therefore, X has a negative binomial distribution with
p = 0.0005 and r = 3
 E(X) = 3/0.0005 = 6000 requests
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
NEGATIVE BIONOMIAL
DISTRIBUTION
EXAMPLE
 What is the probability that all three servers fail
within five requests?
 The probability is P(X ≤ 5)

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 A set of N objects contains
K objects classified as successes
 N - K objects classified as failures
 A sample of size n objects is selected randomly
(without replacement) from the N objects, where k ≤
N and n ≤ N
 Let the random variable X denote the number of
successes in the sample.
 Then X is a hypergeometric random variable and

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
Hypergeometric distributions for selected values of N, K and n
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  Aa day’s production of 850 manufactured parts
contains 50 parts that do not conform to
customer requirements
 Two parts are selected at random, without
replacement from the day’s production
 Let A and B denote the events that the first and
second parts are nonconforming, respectively
 This experiment is fundamentally different from
the examples based on the binomial distribution
 In this experiment, the trials are not independent (in
the unusual case that each unit selected is replaced
before the next selection, the trials are independent)

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  Let X equal the number of nonconforming
parts in the sample. Then
 P(X = 0) P(both parts conform) = (800/850)
(799)(849) = 0.886
 P(X = 1) = P(first part selected conforms and
the second part selected does not, or the first
part selected does not and the second part
selected conforms)
= (800/850)(50/849) + (50/850)(800/849)=
0.111
 P(X = 2) = P(both parts do not conform)

=(50/850)(49/849) = 0.003
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  This example can be reanalyzed by using
the general expression in the definition of a
hypergeometric random variable. That is,

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  If X is a hypergeometric random variable with
parameters N and K and n, then

μ = E(X) = np

and σ2 = V(X) = np(1 – p)( N – n )

N-1
where, p = K /N

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 Given an interval of real numbers, assume counts occur at
random throughout the interval.
 If the interval can be partitioned into subintervals of small enough
length such that
1. The probability of more than one count in a subinterval is zero,
2. The probability of one count in a subinterval is the same for all
subintervals and proportional to the length of the subinterval,
3. The count in each subinterval is independent of other
subintervals, the random experiment is called a Poisson
process.
 The random variable X that equals the number of counts in the
interval is a Poisson random variable with parameter 0 < λ,
and the probability mass function of X is

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 Consider the transmission of n bits over a digital comm. channel
 Let the random variable X = number of bits in error
 When the probability that a bit is in error is constant and the
transmissions are independent, X has a binomial distribution
 Let p = probability (a bit is in error).
 Let λ = pn  E(x) = pn = λ and

 Now, suppose that the number of bits transmitted increases and

the probability of an error decreases exactly enough that pn
remains equal to a constant.
 That is, n increases and p decreases accordingly, such that E(X)
remains constant. Then, with some work, it can be shown that

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 Poisson distributions for selected values of parameters
Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
 Contamination is a problem in manufacture of optical storage disks
 The number of particles of contamination that occur on an optical
disk has a Poisson distribution, and the average number of particles
per centimeter squared of media surface is 0.1
 The area of a disk under study is 100 squared centimeters
 Let X = the number of particles in the area of a disk under study
E(X) = 100 cm2 × 0.1 particles/cm2 =10 particles
 The probability that 12 particles occur in the area of a disk under
study
 The probability that zero particles occur in the area of the disk under
study
 The probability that 12 or fewer particles occur in the area

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid
  If X is a Poisson random variable with
parameters λ, then

μ = E(X) = np = λ
and σ2 = V(X) = λ

Textbook: Applied Statistics and Probability for Engineers by Douglas C. Montgomery & George C. Runger
Analysis of Stochastic Processes: Likelihood by Dr. Ahmar Rashid