Chapter 4

Special Probability
Distributions

4.1 Special Discrete Probability Distributions

We will consider special discrete distributions that are particularly important
in probability theory and statistics. In fact, one needs only a handful of
important probability distributions to describe many of the discrete random
variables encountered in practice.

Binomial Distribution
The binomial distribution is obtained if we are interested in the number of
times an event A occurs in n independent performances of an experiment,
assuming that A has probability (called success) P (A) = p in a single trial.
Then q = 1 − p is the probability that in a single trial the event does not
occur (called failure).

In a binomial distribution, each trial is called Bernoulli trial and the ex-
periment process Bernoulli process. 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, p, remains constant from trial to trial

4. The repeated trials are independent.

1
 Class Notes on
4.1. DISCRETE PRO. DIST. Applied Probability and Statistics ECEG-342

Definition 1. The probability that the event will happen exactly x times in n
trials (i.e., x successes and n − x failures) is given by the probability function
 
n x n−x
f (x) = P (X = x) = p q
x
where the binomial random variable X denotes the number of success in n
trials and x = 0, 1, . . ..

Example 4.1: Find the probability of getting exactly 2 heads in 6 tosses of a fair
coin.

Example 4.2: The probability that a patient recovers from rare blood disease is
0.4. If 15 people are known to have contracted this disease, what is the probability
that
1. at least 10 survive

2. from 3 to 8 survive

3. exactly 5 survive?

Theorem 1. The mean and variance of a binomial distribution are

µ = np and σ 2 = npq.

Exercise 4.1: Prove the above theorem.

Multinomial Distribution
Suppose that events A1 , A2 , . . . , Ak can occur with probabilities p1 , p2 , . . . , pk
where p1 + p2 + . . . + pk = 1. If X1 , X2 , . . . , Xk are the random variables
respectively giving the number of times A1 , A2 , . . . , Ak occur in a total of n
independent trials, so that x1 + x2 + . . . + xk = 1, then

f (x1 , x2 , . . . , xk ) = P (X1 = x1 , X2 = x2 , . . . , Xk = xk )
n!
= px1 px2 . . . pxkk
n1 !n2 ! . . . nk ! 1 2
This distribution is a generalization of the binomial distribution.

Example 4.3: If a fair die is tossed 12 times, find the probability of getting 1, 2,
3, 4, 5, and 6 points exactly twice.

Murad Ridwan, 2 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.1. DISCRETE PRO. DIST. Applied Probability and Statistics ECEG-342

Example 4.4: If a pair of fair dice are tossed 6 times, what is the probability of
obtaining a total of 7 or 11 twice, a matching pair once, and any other combination
3 times?

Hypergeometric Distribution
The binomial distribution is important in sampling with replacement. Sup-
pose that a box contains N things, for example screws, M of which are de-
fective. If we want to draw a screw at random, the probability of obtaining
a defective screw is
M
p=
N
Hence in drawing a sample of n screws with replacement, the probability of
obtaining precisely x defective screws is
   x  n−x
n M M
f (x) = 1− x = 0, 1, . . . , n
x N N
In sampling without replacement the probability is
  
M N −M
x n−x
f (x) =   x = 0, 1, . . . , n
N
x

This distribution is called hypergeometric distribution.

Exercise 4.2: Prove the above assertion.

Theorem 2. The mean and variance of the hypergeometric distribution are:

M nM (N − M )(N − n)
µ=n σ2 =
N N 2 (N − 1)
Exercise 4.3: Prove the above theorem.

Example 4.5: We want to draw random samples of two gaskets from a box con-
taining 10 gaskets, three of which are defective. Find the probability distribution
of the random variable which is the number of defective in the sample

1. if the sample is done with replacement

2. if the sample is done without replacement.

Murad Ridwan, 3 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.1. DISCRETE PRO. DIST. Applied Probability and Statistics ECEG-342

Poison Distribution
Experiments yielding numerical values of a random variable X which are the
number of outcomes occurring during a given time interval or in a specific
region, are called poisson experiments.
The given time interval might be any length- minutes, a day, a week or a
year. For example, X may represent the number of telephone calls per hour
received by an office, or the number of postponed games due to rain in a
rainy season, or the number of cars passing an intersection per unit interval
of time.
The specified region could be a line segment, an area, a volume or a piece of
material. In these cases, X might represent the number of bacteria in a given
culture, or the number of typing errors per page or the number of defects per
unit length of wire or unit area of textile.
More examples of events that may be modeled as a Poisson distribution
include:

• The number of cars that pass through a certain point on a road (suffi-
ciently distant from traffic lights) during a given period of time.

• The number of spelling mistakes one makes while typing a single page.

• The number of phone calls at a call center per minute.

• The number of times a web server is accessed per minute.

• The number of roadkill (animals killed) found per unit length of road.

• The number of mutations in a given stretch of DNA after a certain

amount of radiation.

• The number of unstable nuclei that decayed within a given period of

time in a piece of radioactive substance. The radioactivity of the sub-
stance will weaken with time, so the total time interval used in the
model should be significantly less than the mean lifetime of the sub-
stance.

• The number of pine trees per unit area of mixed forest.

• The number of stars in a given volume of space.

• The number of soldiers killed by horse-kicks each year in each corps

in the Prussian cavalry. This example was made famous by a book of
Ladislaus Josephovich Bortkiewicz (18681931).

Murad Ridwan, 4 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.1. DISCRETE PRO. DIST. Applied Probability and Statistics ECEG-342

• The distribution of visual receptor cells in the retina of the human eye.

• The number of light bulbs that burn out in a certain amount of time.

• The number of viruses that can infect a cell in cell culture.

• The number of hematopoietic stem cells in a sample of unfractionated

bone marrow cells.

• The number of inventions of an inventor over their career.

• The number of particles that ”scatter” off of a target in a nuclear or

high energy physics experiment.
A Poisson process possesses the following properties:
1. The number of outcomes occurring in one time interval or specified
region is independent of the number that occur in any other disjoint
time interval or region of space. In this way Poisson process is said to
possess no memory.

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.
The mean number of outcomes is computed from µ = λt, where t is the spe-
cific ‘time’ or ‘region’ of interest and λ is the rate of occurrence of outcomes.

Definition 2. The probability distribution of the Poisson random variable

X, representing the number of outcomes occurring in a given time interval
or specific region denoted by t, is given by
e−λt (λt)x e−µ µx
f (x) = = x = 0, 1, 2, . . .
x! x!
where λ is the average number of outcomes per unit time or region.

Theorem 3. The mean and variance of the Poisson distribution both have
the value λt, i.e.,
µ = σ 2 = λt

Murad Ridwan, 5 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.2. THE NORMAL DISTRIBUTION Applied Probability and Statistics ECEG-342

Exercise 4.4: Prove the above theorem.

Example 4.6: The average number of radioactive particles passing through a

counter during 1 millisecond in a laboratory experiment is 4. What is the proba-
bility that 6 particles enter the counter in a given millisecond?

Example 4.7: The average number of oil tankers arriving each day at a certain
port city is known to be 10. The facilities at the port can handle at most 15
tankers per day. What is the probability that on a given day tankers will have to
be sent away?

4.2 The Normal Distribution

The normal (or Gaussian) distribution is the most important continuous
probability distribution in the entire field of statistics.
The normal distribution approximately describes many phenomena that oc-
cur in nature, industry, and research. Physical measurement in areas such
as meteorological experiments, rainfall studies, and measurements on man-
ufactured parts are often more than adequately described with a normal
distribution.

Definition 3. The probability density function of the normal random variable

X, with mean µ and variance σ 2 , is
1 1 x−µ 2
f (x) = √ e− 2 ( σ ) , −∞ < x < ∞
2πσ

The normal distribution has the cumulative distribution function

Z x
F (x) = f (v)dv
−∞
Z x
1 1 v−µ 2
=√ e− 2 ( σ ) dv
2πσ −∞
Then

P (a ≤ X ≤ b) = F (b) − F (a)
Z b
1 1 x−µ 2
=√ e− 2 ( σ ) dx
2πσ a

Murad Ridwan, 6 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.2. THE NORMAL DISTRIBUTION Applied Probability and Statistics ECEG-342

Figure 4.1: Normal Distribution Curves

The above integral cannot be evaluated by elementary methods, but can be

represented in terms of the integral
Z z
1 1 2
Φ(z) = √ e− 2 u du
2π −∞
which is the shaded area under the curve in figure 4.2.

Figure 4.2: The Standard Normal Distribution

Φ(z) is the distribution function of the standard normal distribution, i.e., the
normal distribution with mean 0 and variance 1. It has been extensively

Murad Ridwan, 7 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.
 Class Notes on
4.2. THE NORMAL DISTRIBUTION Applied Probability and Statistics ECEG-342

tabulated (see attached table).

F (x) can be expressed in terms of Φ(z) by setting

v−µ
= u.
σ
x−µ
Then dv = σdu and we integrate with respect to u from −∞ to z = σ

Z x−µ
1 σ 1 2
F (x) = √ e− 2 u σdu
2πσ −∞
Z x−µ
1 σ 1 2
=√ e− 2 u du
2π
 −∞ 
x−µ
=Φ
σ

Therefore

P (a ≤ X ≤ b) = F (b) − F (a)
   
b−µ a−µ
=Φ −Φ
σ σ
Example 4.8: Given a normal distribution with µ = 50 and σ = 10, find the
probability that X assumes a value between 45 and 62.

Example 4.9: Let X be standard normal. Determine c such that

1. P (X ≥ c) = 10%

2. P (X ≤ c) = 5%

3. P (0 ≤ X ≤ c) = 45%

4. P (−c ≤ X ≤ c) = 99%

Example 4.10: A certain type of storage battery lasts on the average 3 years, with
a standard deviation of 0.5 years. assuming that the battery lives are normally
distributed, find the probability that a given battery will last less than 2.3 years.

Murad Ridwan, 8 of 8
Dep. of Electrical & Computer Engineering
AAiT, Addis Ababa University.
Jul 2010.