Engineering Statistics (I)

Second Semester 2023/2024

Lecturer: Dr Mohannad Jreissat
Department of Industrial Engineering
School of Engineering

CHAPTER THREE & FOUR - PART II

Random Variables and Probability Distributions

Textbook:
Applied Statistics and Probability for Engineers, by
D. Montgomery and G. Runger, 6th edition, Wiley.

Email: m.jreissat@ju.edu.jo
Office: IE
CHAPTER THREE & FOUR

3.1 Probability Distributions and 3.6 Geometric and Negative

Probability Mass Functions Binomial Distributions
3.2 Cumulative Distribution 3.7 Hypergeometric Distribution
Functions 3.8 Poisson Distribution
3.3 Mean and Variance of a
Discrete Random Variable
3.4 Discrete Uniform Distribution
3.5 Binomial Distribution
4.1 Probability Distributions and Probability 4.7 Exponential Distribution
Density Functions 4.8 Erlang and Gamma Distributions
4.2 Cumulative Distribution Functions 4.9 Weibull Distribution
4.3 Mean and Variance of a Continuous 4.10 Lognormal Distribution
Random Variable 4.11 Beta Distribution
4.4 Continuous Uniform Distribution
4.5 Normal Distribution
4.6 Normal Approximation to the Binomial
and Poisson Distributions
Some Discrete Probability Distributions
Introduction
◼ Often, the observations generated by different statistical experiments
have the same general type of behavior.
◼ The discrete random variables associated with these experiments can
be described by essentially the same probability distribution in a single
formula.

◼ In fact, one needs only a handful of important probability distributions

to describe many of the discrete random variables encountered in
practice.
◼ In this chapter, we are going to present these commonly used
distributions with various examples.
Discrete Uniform Distribution
◼ If the random variable X assumes the values x1, x2, ..., xk, with equal probabilities,
then the discrete uniform distribution is given by
1
f ( x; k ) = , x = x1 , x2 , , xk
k

When a light bulb is selected at random from a box that contains

a 40-watt bulb, a 60-watt bulb, a 75-watt bulb, and a 100-watt
bulb, each element of the sample space S = {40, 60, 75, 100}
occurs with probability 1/4.
Therefore, we have a uniform distribution, with
1
f ( x; 4) = , x = 40, 60, 75,100
4
Discrete Uniform Distribution
When a dice is tossed, each element of the sample space S = {1, 2, 3, 4, 5, 6}
occurs with probability 1/6.
Therefore, we have an uniform distribution with
1
f ( x;6) = , x = 1, 2,3, 4,5, 6
6
 Bernoulli Process
◼ An experiment often consists of repeated trials, each with two
possible outcomes that may be labelled success or failure. We
may choose to define either outcome as a success.
◼ The process is referred to as a Bernoulli process.
◼ Each trial is called a Bernoulli trial.

◼ Strictly speaking, the Bernoulli process must possess the following

properties:
1. The experiment consists of n repeated trials.
2. Each trial results in an outcome that may be classified as a
success or a failure.
3. The probability of success, denoted by p, remains constant from
trial to trial.
4. The repeated trials are independent.
Bernoulli Process
Consider the set of Bernoulli trials where three items are selected at
random from a manufacturing process, inspected, and classified as
defective or non-defective. A defective item is designated a success.
The number of successes is a Random Variable X assuming integer
values from 0 to 3.

The items are selected independently from a process, and we shall

assume that it produces 25% defectives.
The probability of the outcome NDN can be calculated as

 3  1  3  9
P ( NDN ) = P ( N ) P ( D ) P ( N ) =     =
 4  4  4  64
Bernoulli Process
The probabilities for the other possible outcomes can also be
calculated to result in the probability distribution of X.

◼ The number X of successes in n Bernoulli trials is called a binomial

random variable.
◼ The probability distribution of this discrete random variable is called
the binomial distribution and denoted by b (x; n, p).

9
P( X = 2) = f (2) = b(2 : 3, ) =
1
4
64
Binomial Distribution
◼ Binomial Distribution| A Bernoulli trial can result in a success with probability p
and a failure with probability q = 1 – p. Then the probability distribution of the
binomial random variable X, the number of successes in n independent trials, is

b( x : n, p) = n C x p x q n − x , x = 0,1, 2,..., n
◼ The mean and variance of the binomial distribution b (x; n, p) are
 = np  2 = npq

The probability that a certain kind of component will survive a given

shock test is 3/4. Find the probability that exactly 2 of the next 4
components tested will survive.

3 2 2
p=  3  3   1  = 54
4 b  2 : 4,  = 4 C2    
 4 4 4 256
Binomial and Multinomial Distributions
The probability that a patient recovers from a rare blood disease is
0.4. If 15 people are known to have contracted this disease, what is
the probability that (a) at least 10 survive, (b) from 3 to 8 survive,
and (c) exactly 5 survive?

Let X be the number of people that survive. Table A.1 gives help.

9
(a) P ( X  10) = 1 − P( X  10) = 1 −  b( x;15, 0.4) = 1 − 0.9662 = 0.0338
x =0
15
Can you calculate
manually? ?  b( x;15, 0.4) =
x =10

8 8 2
(b) P(3  X  8) =  b( x;15, 0.4) =  b( x;15, 0.4) −  b( x;15, 0.4)
x =3 x =0 x =0

= 0.9050 − 0.0271 = 0.8779

(c) P( X = 5) = b(5;15, 0.4) = 15 C5 (0.4)5 (0.6)10 = 0.1859

Table A.1 Binomial Probability Sums
Binomial and Multinomial Distributions
A large chain retailer purchases a certain kind of electronic device from a
manufacturer. The manufacturer indicates that the defective rate of the
device is 3%.
(a) The inspector of the retailer randomly picks 20 items from a
shipment. What is the probability that there will be at least one
defective item among these 20?
(b) Suppose that the retailer receives 10 shipments in a month, and the
inspector randomly tests 20 devices per shipment. What is the
probability that there will be 3 shipments containing at least one
defective device?

Let X be the number of defective devices among the 20 items.

(a) P( X  1) = 1 − P( X  1) = 1 − P ( X = 0) = 1 − 20 C0 (0.03)0 (1 − 0.03) 20 = 0.4562

(b) p = 0.4562  P(Y = 3) = b(3;10, 0.4562) = 10 C3 (0.4562)3 (1 − 0.4562)10−3 = 0.1602

Binomial and Multinomial Distributions
It is conjectured that an impurity exists in 30% of all drinking wells in a
certain rural community. In order to gain some insight into this problem,
it is determined that some tests should be made. It is too expensive to
test all of the many wells in the area, so 10 were randomly selected for
testing.
(a) Using the binomial distribution, what is the probability that exactly
three wells have the impurity assuming that the conjecture is
correct?
(b) What is the probability that more than three wells are impure?

(a) P( X = 3) = 10 C3 (0.3)3 (1 − 0.3)10−3 = 0.2668

(b) P( X  3) = 1 − P( X  3)
Try also to use Table A.1
3
= 1 −  b( x;10, 0.3) to find this value ?
x =0

= 1 − 0.0282 + 0.1211 + 0.2335 + 0.2668

= 0.3504
Binomial and Multinomial Distributions
Consider the previous “drinking wells” example. The “30% are impure” is
merely a conjecture put forth by the area water board.
Suppose 10 wells are randomly selected, and 6 are found to contain the
impurity. What does this imply about the conjecture? Use a probability
statement.

P( X = 6) = 10 C6 (0.3)6 (1 − 0.3)10−6 = 0.0368

 Should the 30% impurity conjecture be true, there is only a 3.68%

chance that it stands after 6 wells are found contaminated.
 The investigation suggests that the impurity problem is much
more severe than 30%.
Binomial and Multinomial Distributions
◼ The binomial experiment becomes a multinomial experiment if we let
each trial have more than 2 possible outcomes.

◼ |Multinomial Distribution| If a given trial can result in the k outcomes

E1, E2, ..., Ek with probabilities p1, p2, .., pk, then the probability
distribution of the random variables X1, X2, ..., Xk, representing the
number of occurrence for E1, E2, ..., Ek in n independent trials is

n!
f ( x1 , x2 ,..., xk ; p1 , p2 ,..., pk , n) = p1x1 p2x2 ... pkxk
x1 ! x2 !...xk !
with
k k

x i = n and p
i =1
i =1
i =1
Binomial and Multinomial Distributions
The complexity of arrivals and departures into an airport are such that
computer simulation is often used to model the “ideal” conditions.
For a certain airport containing three runways it is known that in the
ideal setting the probabilities that the individual runways are accessed
by a randomly arriving commercial jet are 2/9, 1/6, and 11/18 for
runway1, runway2, and runway3, respectively.
If there are 6 randomly arriving airplanes, what is the probability that
2 airplanes will do the landing in runway1, 1 in runway2, and 3 in
runway3?

2 1 3
 2 1 11  6!  2   1   11 
f  2,1,3; , , , 6  =       = 0.1127
 9 6 18  2!1!3!  9   6   18 

What is the probability that 2 airplanes will do

the landing in runway 1? ?
Hypergeometric Distribution
◼ As opposed to the binomial distribution, the hypergeometric
distribution is based on the sampling done without replacement. The
independence among trials is not required.
◼ Applications for the hypergeometric distribution are found in many
areas, with heavy uses in acceptance sampling, electronic sampling,
and quality assurance.
◼ The experiment where the hypergeometric distribution applies must possess the
following two properties:
1. A random sample of size n is selected without replacement from N items
2. k of the N items may be classified as successes, and N –k are classified as failures.

◼ The number X of successes of a hypergeometric experiment is called a

hypergeometric random variable.
◼The hypergeometric distribution of such variable is denoted by h (x ; N, n, k)
Hypergeometric Distribution
A particular part that is used as an injection device is sold in lots of 10.
The producer feels that the lot is deemed acceptable if no more that one
defective is in the lot.
Some lots are sampled and the sampling plan involves random sampling
and testing 3 of the parts out of 10. If none of the 3 are defective, the lot is
accepted. Give comment on the utility of this plan.

C C  In case there are 2 defectives, there is

P( X = 0) = 0 8 3 = 0.467
2
still a chance of 46.7% that the lot is
10 C3
accepted.

C0 7 C3  In case there are 3 defectives, there is

P( X = 0) = 3
= 0.291 still a chance of 29.1% that the lot is
10 C3 accepted.

 As conclusion, a plan to do this kind of quality control is faulty. Unacceptable

lot can still be accepted with high probability.
 3 samples are not enough. The sample size must be increased.
Hypergeometric Distribution
◼ The probability distribution of the hypergeometric random variable X,
the number of successes in a random sample of size n selected from N
items of which k are labeled success and N–k labeled failure, is

Cx N −k Cn − x
h( x; N , n, k ) =k
, x = 0,1, 2,..., n
N Cn

◼ The mean and variance of the hypergeometric distribution h(x;N,n,k)

are
nk N −n k  k 
= and 2 = n 1 − 
N N −1 N  N 
Hypergeometric Distribution
Lots of 40 components each are called unacceptable if they contain as
many as 3 defectives or more. The procedure for sampling the lot is to
select 5 components at random and to reject the lot if a defective is
found.
(a) What is the probability that exactly 1 defective is found in the sample
if there are 3 defectives in the entire lot?
(b) Find the mean and variance of the random variable and use
Chebyshev’s theorem to interpret the interval μ ± 2σ.

C1 37 C4  Again, this method of testing is not

(a) h(1; 40,5,3) = 3
= 0.3011 acceptable, since it detects a bad lot
40 C5 (with 3 defectives) only about 30% of
the time
nk (5)(3) 3
(b) = = = = 0.375
N 40 8
N −n k  k   40 − 5   3  3 
2 = n 1 −  =    
(5) 1 −  = 0.3113
N − 1 N  N   40 − 1   40  40 
 = 0.558  Chebyshev Theorem: In at least 3/4 of
the time, the number of defectives will
be between –0.741 and 1.491
components
Hypergeometric Distribution
◼ If the number of sample n is small compared to the sample size N, the
nature of the N items changes very little in each draw, although without
replacement.
◼ In this case, where n/N ≤ 0.05, the value of binomial distribution can be
used to approximate the value of hypergeometric distribution.

A manufacturer of automobile tires reports that among a shipment of

5000 sent to a local distributor, 1000 are slightly blemished. If one
purchase 10 of these tires at random from the distributor, what is the
probability that exactly 3 are blemished?

C3 4000 C7
h(3;5000,10,1000) = 1000
= 0.2015  Exact
hypergeometric
5000 C10 probability
1
p ,
5
3 10 −3
 1 1  4  Approximation using
b  3;10,  = 10 C3     = 0.2013 binomial distribution
 5 5  5
Negative Binomial Distribution
◼ Consider an experiment where the properties are the same as those listed for
a binomial experiment, with the exception that the trials will be repeated
until a fixed number of successes occur.
◼ We are interested in the probability that the kth success occurs on the xth trial.
◼ This kind of experiment is called negative binomial experiment.

◼ The number X of trials to produce k successes in a negative binomial

experiment is called a negative binomial random variable, and its
probability distribution is called the negative binomial distribution.

◼ |Negative Binomial Distribution| If repeated independent trials can result

in a success with probability p and a failure with probability q = 1–p, then
the probability distribution of the random variable X, the number of the
trial on which the kth success occurs, is

k x −k
b* ( x; k , p) = C
x −1 k −1 p q , x = k , k + 1, k + 2,...
Negative Binomial Distribution
In an NBA (National Basketball Association) championship series, the
team which wins four games out of seven will be the winner. Suppose
that team A has probability 0.55 of winning over the team B and both
teams A and B face each other in the championship games.
(a) What is the probability that team A will win the series in six games?
(b) What is the probability that team A will win the series?

6−4
(a) b* (6; 4, 0.55) = C
6 −1 4 −1 (0.55) 4
(0.45) = 0.1853

(b) P(team A wins the championship series)

= b* (4; 4, 0.55) + b* (5; 4, 0.55) + b* (6; 4, 0.55) + b* (7; 4, 0.55)
= 0.0915 + 0.1647 + 0.1853 + 0.1668 = 0.6083
Negative Binomial Distribution
In an NBA (National Basketball Association) championship series, the
team which wins four games out of seven will be the winner. Suppose
that team A has probability 0.55 of winning over the team B and both
teams A and B face each other in the championship games.
(c) If both teams face each other in a regional playoff series and the
winner is decided by winning three out of five games, what is the
probability that team A will win a playoff?

(c) P(team A wins the regional series)

= b* (3;3, 0.55) + b* (4;3, 0.55) + b* (5;3, 0.55)
= 0.1664 + 0.2246 + 0.2021 = 0.5931
Geometric Distribution
◼ If we consider the special case of the negative binomial distribution
where k = 1, we have a probability distribution for the number of trials
required for a single success.

◼ If repeated independent trials can result in a success with probability p

and a failure with probability q = 1–p, then the probability distribution of
the random variable X, the number of the trial on which the first
success occurs, is
g ( x; p ) = pq x −1 , x = 1, 2,3,...

◼ The mean and variance of a random variable following the geometric

distribution are
1 1− p
= and 2 =
p p2
Geometric Distribution
In a certain manufacturing process it is known that, on the average, 1 in
every 100 items is defective. What is the probability that the fifth item
inspected is the first defective item found?

g (5;0.01) = (0.01)(0.99) 4 = 0.0096

At “busy time” a telephone exchange is very near capacity, so callers

have difficulty placing their calls. It may be of interest to know the
number of attempts necessary in order to gain a connection.
Suppose that we let p = 0.05 be the probability of a connection during
busy time. We are interested in knowing the probability that 5 attempts
are necessary for a successful call.

P( X = 5) = g (5;0.05) = (0.05)(0.95) 4 = 0.041

Poisson Distribution and Poisson Process
◼ Experiments yielding numerical values of a random variable X, the
number of outcomes occurring during a given time interval or in a
specified region, are called Poisson experiments.
◼ The time interval may be given in any length, such as minute, day,
week, and month.
◼ The specified region may be a line segment, an area, a volume, or a
piece of material
Properties of Poisson Process
◼ A Poisson experiment is derived from the Poisson process and
possesses the following properties:
1. The number of outcomes occurring in one time interval or specified
region is independent of the number that occurs in any other
disjoint time interval or region of space.
2. The probability that a single outcome will occur during a very short
time interval or in a small region is proportional to the length of the
time interval or the size of the region and does not depend on the
number of outcomes occurring outside this time interval or region.
3. The probability that more than one outcome will occur in such a
short time interval or fall in such a small region is negligible.
Poisson Distribution and Poisson Process
◼ |Poisson Distribution| The probability distribution of the Poisson
random variable X, representing the number of outcomes occurring in
a given time interval or specified region denoted by t, is
e −  t ( t ) x
p( x; t ) = , x = 0,1, 2,...
x!
where λ is the average number of outcomes per unit time or region,
and e = 2.71828.... (natural number).

◼ The mean and variance of the Poisson distribution p(x;λt) both have
the value λt.
Poisson Distribution and Poisson Process
During a laboratory experiment the average number of radioactive
particles passing through a counter in 1 millisecond is 4. What is the
probability that 6 particles enter the counter in a given millisecond?

x = 6, t = 4
e−4 (4)6
p(6; 4) = = 0.1042
6!

Ten is the average number of oil tankers arriving each day at a certain
port city. The facilities at the port can handle at most 15 tankers per day.
What is the probability that on a given day tankers have to be turned
away?
15  Table A.2 gives help
P( X  15) = 1 − P( X  15) = 1 −  p( x;10)
x =0

 e−10 (10)1 e−10 (10)2 e−10 (10)15 

= 1−  + + + 
 1! 2! 15! 
= 1 − 0.9513 = 0.0487
Table A.2 Poisson Probability Sums
Poisson Distribution As a Limit of Binomial
◼ It should be clear from the three properties of the Poisson process that
the Poisson distribution relates to the binomial distribution.
◼ In the case of the binomial, if n is quite large and p is small, the
conditions begin to simulate the continuous space or time region
implications of the Poisson process.

◼ Poisson distribution can be taken as a limiting form of the binomial

distribution when n → ∞ and p → 0, and np remains constant.
◼ If the conditions are fulfilled, the Poisson distribution can be used with
μ = np, to approximate binomial distribution.

◼ Let X be a binomial random variable with probability distribution

b(x;n,p). When n → ∞ and p → 0, and μ = np remains constant,
b( x; n, p ) → p ( x,  )
Poisson Distribution and Poisson Process
In a certain industrial facility accidents occur infrequently. It is known
that the probability of an accident on any given day is 0.005 and
accidents are independent of each other.
(a) What is the probability that in any given period of 400 days there will
be an accident on one day?
(b) What is the probability that there are at most three days with an
accident?

x = 1,  t = (0.005)(400) = 2
e−2 (2)1  Considered as
(a) p(1; 2) = = 0.2707
1! Poisson process

b(1; 400, 0.005) = C (0.005)1

(0.095) 399
= 0.2707  Considered as
400 1 Bernoulli process

3 3
e−2 (2) x
(b) P( X  3) =  p( x; 2) =  = 0.8571
x =0 x =0 x!
3
P( X  3) =  b( x; 400, 0.005) = 0.8571
x =0
Poisson Distribution and Poisson Process
In a manufacturing process where glass products are produced, defects
or bubbles occur, occasionally rendering the piece undesirable for
marketing. It is known that, on average, 1 in every 1000 of these items
produced has one or more bubbles. What is the probability that a random
sample of 8000 will yield fewer than 7 items possessing bubbles?

 = (8000)(0.001) = 8
6 6
P( X  7) =  b( x;8000, 0.001)   p( x;8) = 0.3134
x =0 x =0

 Actually a  Solved by
problem for approximation
Binomial using Poisson
Distribution Distribution
Recap…
(With a constant probability of success)
Some Continuous Probability Distributions
Continuous Uniform Distribution
◼ |Uniform Distribution| The density function of the continuous uniform
random variable X on the interval [A, B] is
 1
B − A , A  x  B
f ( x; A, B ) = 
0, elsewhere

◼ The mean and variance of the uniform distribution are
A+ B ( B − A)2
= and  =
2

2 12

 The uniform density

function for a random
variable on the interval
[1, 3]
Continuous Uniform Distribution
Suppose that a large conference room for a certain company can be reserved for
no more than 4 hours. However, the use of the conference room is such that both
long and short conference occur quite often. In fact, it can be assumed that length
X of a conference has a uniform distribution on the interval [0, 4].
(a) What is the probability density function?
(b) What is the probability that any given conference lasts at least 3 hours?

1
4 , 0  x  4
(a) f ( x) = 
0, elsewhere


1
4
1
(b) P  X  3 =    dx =
3
4 4
Normal Distribution
◼ Normal distribution is the most important continuous probability
distribution in the entire field of statistics.
◼ Its graph, called the normal curve, is the bell-shaped curve which
describes approximately many phenomena that occur in nature,
industry, and research.
◼ The normal distribution is often referred to as the Gaussian
distribution, in honor of Karl Friedrich Gauss, who also derived its
equation from a study of errors in repeated measurements of the same
quantity.

 The normal curve

Normal Distribution
◼ A continuous random variable X having the bell-shaped distribution as
shown on the figure is called a normal random variable.

◼ The density function of the normal random variable X, with mean μ and
variance σ 2, is
1  x− 
2

1 −  
n( x;  ,  ) = e 2  
, −  x  
2

where π = 3.14159... and e = 2.71828...

Normal Curve

 μ1 < μ2, σ1 = σ2  μ1 = μ2, σ1 < σ2

 μ1 < μ2, σ1 < σ2

Normal Curve
f(x) ❖The mode, the point where
the curve is at maximum

❖Concave downward

❖Point of inflection
σ σ

❖Concave upward

❖Approaches zero
asymptotically

x
μ
❖Total area under the curve and ❖Symmetry about a vertical
above the horizontal axis is axis through the mean μ
equal to 1
Area Under the Normal Curve
◼ The area under the curve bounded by two ordinates x = x1 and
x = x2 equals the probability that the random variable X assumes
a value between x = x1 and x = x2.

1  x− 
2
x2 x2
1 −  
P ( x1  X  x2 ) =  n( x;  ,  )dx = e
2  
dx
x1 2 x1
Area Under the Normal Curve
◼ As seen previously, the normal curve is dependent on the mean μ and
the standard deviation σ of the distribution under investigation.
◼ The same interval of a random variable can deliver different probability
if μ or σ are different.

 Same interval, but different probabilities for two

different normal curves
Area Under the Normal Curve
◼ The difficulty encountered in solving integrals of normal density
functions necessitates the tabulation of normal curve area for quick
reference.
◼ Fortunately, we are able to transform all the observations of any normal
random variable X to a new set of observation of a normal random
variable Z with mean 0 and variance 1.

X −
Z=

1  x− 
2
x2
1 −  
e
2  
P ( x1  X  x2 ) = dx
2 x1

z2 z2
1 −
=
2
e
z1
2
dz

z2

=  n( z;0,1)dz = P( z1  Z  z2 )
z1
Area Under the Normal Curve
◼ The distribution of a normal random variable with mean 0 and variance
1 is called a standard normal distribution.
Table A.3 Normal Probability Table
Interpolation
◼ Interpolation is a method of constructing new data points within the
range of a discrete set of known data points.
◼ Examine the following graph. Two data points are known, which are
(a,f (a)) and (b,f (b)).
◼ If a value of c is given, with a < c < b, then the value of f (c) can be
estimated.
◼ If a value of f (c) is given, with f (a) < f (c) < f (b), then the value of c can
be estimated.

c−a
f (c ) = f ( a ) + ( f (b) − f (a) )
f (b)
b−a
f (c ) ?
f (a) f (c ) − f ( a )
c =a+ (b − a )
f (b) − f (a)
a c? b
Interpolation

 P(Z < 1.172)? Answer: 0.8794

 P(Z < z) = 0.8700, z = ? 1.126
Area Under the Normal Curve
Given a standard normal distribution, find the area under the curve that
lies (a) to the right of z = 1.84 and (b) between z = –1.97 and z = 0.86.

(a) P ( Z  1.84) = 1 − P ( Z  1.84)

= 1 − 0.9671
= 0.0329

(b) P(−1.94  Z  0.86) = P( Z  0.86) − P( Z  −1.94)

= 0.8051 − 0.0244
= 0.7807
Area Under the Normal Curve
Given a standard normal distribution, find the value of k such that
(a) P ( Z > k ) = 0.3015, and (b) P ( k < Z < –0.18 ) = 0.4197.

(a) P( Z  k ) = 1 − P( Z  k )

P( Z  k ) = 1 − P( Z  k )
= 1 − 0.3015 = 0.6985
k = 0.52

(b) P(k  Z  −0.18) = P( Z  −0.18) − P( Z  k )

P( Z  k ) = P( Z  −0.18) − P(k  Z  −0.18)

= 0.4286 − 0.4197 = 0.0089
k = − 2.37
Area Under the Normal Curve
Given a random variable X having a normal distribution with μ = 50 and σ
= 10, find the probability that X assumes a value between 45 and 62.

x1 −  45 − 50
z1 = = = −0.5
 10
x2 −  62 − 50
z2 = = = 1.2
 10

P(45  X  62) = P( −0.5  Z  1.2)

= P ( Z  1.2) − P ( Z  −0.5)
= 0.8849 − 0.3085
= 0.5764
Area Under the Normal Curve
Given that X has a normal distribution with μ = 300 and σ = 50, find the
probability that X assumes a value greater than 362.

x− 362 − 300

z= = = 1.24
 50

P ( X  362) = P ( Z  1.24)
= 1 − P( Z  1.24)
= 1 − 0.8925
= 0.1075
Area Under the Normal Curve
Given a normal distribution with μ = 40 and σ = 6, find the value of x that
has (a) 45% of the area to the left, and (b) 14% of the area to the right.

0.45 − 0.4483
(a) P( Z  z ) = 0.45 z = −0.13 + ( −0.12 − (−0.13) ) = −0.1256
0.4522 − 0.4483
x =  + z = 40 + (−0.1256)(6) = 39.2464

2 2 5 4. 0
5 4. 0

3 8 4 4. 0

3 1. 0 − ? 2 1. 0 −
Area Under the Normal Curve
Given a normal distribution with μ = 40 and σ = 6, find the value of x that
has (a) 45% of the area to the left, and (b) 14% of the area to the right.

(b) P( z  Z ) = 0.14 = 1 − P( Z  z )

P( Z  z ) = 1 − 0.14 = 0.86

 z = 1.08
x =  + z = 40 + (1.08)(6) = 46.48
Applications of the Normal Distribution
A certain type of storage battery lasts, on average, 3.0 years, with a
standard deviation of 0.5 year. Assuming that the battery lives are
normally distributed, find the probability that a given battery will last less
than 2.3 years.

x− 2.3 − 3.0

z= = = −1.4
 0.5
P( Z  −1.4) = 0.0808

= 8.08%
Applications of the Normal Distribution
In an industrial process the diameter of a ball bearing is an important
component part. The buyer sets specifications on the diameter to be 3.0 ±
0.01 cm. All parts falling outside these specifications will be rejected.
It is known that in the process the diameter of a ball bearing has a normal
distribution with mean 3.0 and standard deviation 0.005.
On the average, how many manufactured ball bearings will be scrapped?

P (2.99  X  3.01) = P( −2  Z  2)
= P( Z  2) − P( Z  −2)
= 0.9772 − 0.0228
= 0.9544

x1 − 
2.99 − 3.0  95.44% accepted
z1 = = = −2
 0.005
 4.56% rejected
x −  3.01 − 3.0
z2 = 2 = = +2
 0.005
Applications of the Normal Distribution
A certain machine makes electrical resistors having a mean resistance of
40 Ω and a standard deviation of 2 Ω. It is assumed that the resistance
follows a normal distribution.
What percentage of resistors will have a resistance exceeding 43 Ω if:
(a) the resistance can be measured to any degree of accuracy.
(b) the resistance can be measured to the nearest ohm only.

43 − 40
(a) z= = 1.5
2
P( X  43) = P( Z  1.5) = 1 − P ( Z  1.5) = 1 − 0.9332 = 0.0668 = 6.68%

43.5 − 40
(b) z= = 1.75
2
P( X  43.5) = P( Z  1.75) = 1 − P( Z  1.75) = 1 − 0.9599 = 0.0401 = 4.01%

 As many as 6.68%–4.01% = 2.67% of the

resistors will be accepted although the value is
greater than 43 Ω due to measurement limitation
Applications of the Normal Distribution
The average grade for an exam is 74, and the standard deviation is 7. If
12% of the class are given A’s, and the grade are curved to follow a
normal distribution, what is the lowest possible A and the highest
possible B?

P( Z  z ) = 0.12
P( Z  z ) = 1 − P( Z  z ) = 1 − 0.12 = 0.88

 z = 1.175
x =  + z = 74 + (1.175)(7) = 82.225  Lowest possible A is 83
 Highest possible B is 82
Normal Approximation to the Binomial
◼ The probabilities associated with binomial experiments are readily
obtainable from the formula b(x;n, p) of the binomial distribution or
from the table when n is small.
◼ For large n, making the distribution table is not practical anymore.
◼ Nevertheless, the binomial distribution can be nicely approximated by
the normal distribution under certain circumstances.
Normal Approximation to the Binomial
◼ If X is a binomial random variable with mean μ = np and variance σ2 =
npq, then the limiting form of the distribution of
X − np
Z=
npq
as n → ∞, is the standard normal distribution n(z;0, 1).

 Normal approximation of b(x; 15, 0.4)

 Each value of b(x; 15, 0.4) is approximated by
P(x–0.5 < X < x+0.5)
Normal Approximation to the Binomial
P( X = 4) = b(4;15, 0.4)
= 15 C4 (0.4) 4 (0.6)11
= 0.1268

P( X = 4)  P(3.5  X  4.5)
 P(−1.32  Z  −0.79)
 0.1214
 Normal approximation of
9
b(4;15, 0.4) and  b( x;15, 0.4)
x =7
9
P(7  X  9) =  b( x;15, 0.4)
x =7

= 0.3564
 = np = (15)(0.4) = 6
P(7  X  9) = P(6.5  X  9.5)
 = npq = (15)(0.4)(0.6) = 1.897
 P (0.26  Z  1.85)
 0.3652
Normal Approximation to the Binomial
◼ The degree of accuracy, that is how well the normal curve fits the
binomial histogram, will increase as n increases.
◼ If the value of n is small and p is not very close to 1/2, normal curve will
not fit the histogram well, as shown below.

b( x;6, 0.2) b( x;15, 0.2)

◼ The approximation using normal curve will be excellent when n is large

or n is small with p reasonably close to 1/2.
◼ As rule of thumb, if both np and nq are greater than or equal to 5, the
approximation will be good.
Normal Approximation to the Binomial
◼ Let X be a binomial random variable with parameters n and p. For large
n, X has approximately a normal distribution with μ = np and σ2 = npq =
np(1–p) and
x
P( X  x) =  b(k ; n, p)
k =0
 area under normal curve to the left of x + 0.5
= P( X  x + 0.5)
 ( x + 0.5) −  
= P Z  
  
and the approximation will be good if np and nq = n(1–p) are greater
than or equal to 5.
Normal Approximation to the Binomial
The probability that a patient recovers from a rare blood disease is 0.4. If
100 people are known to have contracted this disease, what is the
probability that less than 30 survive?

n = 100, p = 0.4  = np = (100)(0.4) = 40

29  = npq = (100)(0.4)(0.6) = 4.899

P( X  30) =  b( x;100, 0.4)
x =0

29.5 − 40
P( X  30)  P ( X  29.5) z= = −2.143
4.899
 P( Z  −2.143)
 0.01608
 After interpolation

 1.608%
 Can you calculate the
exact solution?
Normal Approximation to the Binomial
A multiple-choice quiz has 200 questions each with 4 possible answers of
which only 1 is the correct answer. What is the probability that sheer
guess-work yields from 25 to 30 correct answers for 80 of the 200
problems about which the student has no knowledge?
1
n = 80, p =  = np = (80)( 14 ) = 20
4
 = npq = (80)( 14 )( 34 ) = 3.873
24.5 − 20 30.5 − 20
z1 = = 1.162, z2 = = 2.711
30 3.873 3.873
P(25  X  30) =  b( x;80,
x = 25
1
4 )

 P (24.5  X  30.5)
 P(1.162  Z  2.711)
 P( Z  2.711) − P( Z  1.162)
 0.9966 − 0.8774
 0.1192
Normal Approximation to the Binomial
PU Physics entrance exam consists of 30 multiple-choice questions each
with 4 possible answers of which only 1 is the correct answer. What is
the probability that a prospective students will obtain scholarship by
correctly answering at least 80% of the questions just by guessing?

1
n = 30, p =  = np = (30)( 14 ) = 7.5
4
 = npq = (30)( 14 )( 43 ) = 2.372
30
P( X  24) =  b( x;30,
x = 24
1
4 ) z=
23.5 − 7.5
= 6.745
2.372
 1 − P( X  23.5)

 1 − P( Z  6.745)

 0
 It is practically impossible to get
scholarship just by pure luck in the
entrance exam
Gamma and Exponential Distributions
◼ There are still numerous situations that the normal distribution cannot
cover. For such situations, different types of density functions are
required.
◼ Two such density functions are the gamma and exponential
distributions.
◼ Both distributions find applications in queuing theory and reliability
problems.

◼ The gamma function is defined by


( ) =  x −1e− x dx
0
for α > 0.
Gamma and Exponential Distributions
◼ |Gamma Distribution| The continuous random variable X has a gamma
distribution, with parameters α and β, if its density function is given by

 1  −1 − x 
   ( ) x e , x0
f ( x) = 

0, elsewhere
where α > 0 and β > 0.

◼ |Exponential Distribution| The continuous random variable X has an

exponential distribution, with parameter β, if its density function is
given by
 1 −x 
 e , x0
f ( x) = 

0, elsewhere
where β > 0.
Gamma and Exponential Distributions

 Gamma distributions for certain values of the

parameters α and β
 The gamma distribution with α = 1 is called the
exponential distribution
Gamma and Exponential Distributions
◼ The mean and variance of the gamma distribution are
 =  and  2 =  2

◼ The mean and variance of the exponential distribution are

= and 2 = 2
Applications of Gamma and Exponential Distributions
Suppose that a system contains a certain type of component whose time
in years to failure is given by T. The random variable T is modeled nicely
by the exponential distribution with mean time to failure β = 5.
If 5 of these components are installed in different systems, what is the
probability that at least 2 are still functioning at the end of 8 years?

 5
1
P(T  8) =  e−t 5 dt P( X  2) =  b( x;5, 0.2)
58 x=2
1

= e −8 5  0.2 = 1 −  b( x;5, 0.2)

x =0

 The probability whether the = 1 − 0.7373

component is still functioning at = 0.2627
the end of 8 years

 The probability whether at least

2 out of 5 such component are
still functioning at the end of 8
years
Applications of Gamma and Exponential Distributions
Suppose that telephone calls arriving at a particular switchboard follow a
Poisson process with an average of 5 calls coming per minute.
What is the probability that up to a minute will elapse until 2 calls have
come in to the switchboard?

 = 1 5,  = 2  β is the mean time of the event

of calling
x
1  α is the quantity of the event of
P( X  x) =  xe− x  dx calling
0
 2

1
P( X  1) = 25 xe−5 x dx = 1 − e−5(1) (1 + 5) = 0.96
0
Applications of Gamma and Exponential Distributions
Based on extensive testing, it is determined that the average of time Y
before a washing machine requires a major repair is 4 years. This time is
known to be able to be modeled nicely using exponential function. The
machine is considered a bargain if it is unlikely to require a major repair
before the sixth year.
(a) Determine the probability that it can survive without major repair until
more than 6 years.
(b) What is the probability that a major repair occurs in the first year?


1
(a) P(Y  6) =  e−t 4 dt = e −6 4  0.223  Only 22.3% survives until more
46 than 6 years without major
reparation


1
(b) P(Y  1) = 1 −  e−t 4 dt = 1 − e −1 4  0.221  22.1% will need major reparation
41 after used for 1 year
1
1
=  e−t 4 dt
40
Chi-Squared Distribution
◼ Another very important special case of the gamma distribution is
obtained by letting α = v/2 and β = 2, where v is a positive integer.
◼ The result is called the chi-squared distribution, with a single
parameter v called the degrees of freedom.

◼ The chi-squared distribution plays a vital role in statistical inference. It

has considerable application in both methodology and theory.
◼ Many chapters ahead of us will contain important applications of this
distribution.
Chi-Squared Distribution
◼ |Chi-Squared Distribution| The continuous random variable X has a chi-
squared distribution, with v degrees of freedom, if its density function
is given by
 1 v 2 −1 − x 
 2v 2 (v 2) x e , x0
f ( x) = 

0, elsewhere
where v is a positive integer.

◼ The mean and variance of the chi-squared distribution are

 =v and  2 = 2v
Lognormal Distribution
◼ The lognormal distribution is used for a wide variety of applications.
◼ The distribution applies in cases where a natural log transformation
results in a normal distribution.
Lognormal Distribution
◼ |Lognormal Distribution| The continuous random variable X has a
lognormal distribution if the random variable Y = ln(X) has a normal
distribution with mean μ and standard deviation σ. The resulting
density function of X is
 1 − ln( x ) −  
2
(2 2 )
 2 x e , x0
f ( x) = 

0, x0

◼ The mean and variance of the chi-squared distribution are

 + 2 2 2  + 2 2
E( X ) = e and Var( X ) = e (e − 1)
Lognormal Distribution
Concentration of pollutants produced by chemical plants historically are
known to exhibit behavior that resembles a log normal distribution. This
is important when one considers issues regarding compliance to
government regulations.
Suppose it is assumed that the concentration of a certain pollutant, in
parts per million, has a lognormal distribution with parameters μ = 3.2
and σ = 1.
What is the probability that the concentration exceeds 8 parts per
million?

P( X  8) = 1 − P( X  8)
 ln(8) − 3.2 
P( X  8) = F   = F (−1.12) = 0.1314
 1 
 F denotes the cumulative distribution function of the
standard normal distribution
 a. k. a. the area under the normal curve