Lec Note E6
Lec Note E6
- 6 HPD-DS
Broadly, if the random variable X takes whole numbers from 1 to n , for all i , from 1 i n , the
probability of occurring any value is 1 and if the probabilities do not change in independent repetitive
n
experiments of the random variable, then X is known to be discrete uniform random variable.
Probability Function
When the probability of getting any value for the variable X from 1 to n is equal and is 1 ( n ) the
probability mass function of X is,
1
P ( x) = P ( X = x) = ; x = 1, 2,....,N
N
Here, N is then number of occurrences or the values that can be taken to the random variable.
Example 1 : When rolling an unbiased die with 6 faces, find the probability of getting a value greater
than or equal to 3 and the mean and variance of the value get.
Example 2 : A child is playing a game by tossing an unbiased coin. If he gets a head, he is supposed to
jump 10 times and if he gets a tail, he is supposed to jump 6 times. If X is the number of
times he jumps, find,
i. the probability distribution function of X
iii. the probability that he jumps more than 7 times.
iv. the probability that he jumps less than 3 times.
v. The mean value and the variance of the number of jumps the boy make
Mean
The mean or the expected value of a uniform distribution is, E ( X )
N +1
E (X ) =
2
Variance
Variance of a uniform distribution is Var ( X )
1
January, 2023
Handout No. - 6 HPD-DS
N 2 −1
Var ( X ) =
12
Bernoulli Distribution
If the outcome of a random experiment can be classified only for two categories, such a random
experiment is known as a Bernoulli distribution. As for examples, defectivity and non-defectivity of a
product, success and failure of a laboratory experiment, pass and fail of an examination, gender of a
person can be stated. Commonly, the outcome of such an experiment can be stated as success and failure
and they are denoted as S and F respectively.
Of the two outcomes - based on a Bernoulli trial- a random variable can be defined by taking the
probability of getting a success as p and such an experiment is known as a Bernoulli distribution.
Probability Function
When defining a random variable X , the outcome of a Bernoulli trial gets value 1 and 0 for a S and F
respectively, X is said to have a Bernoulli distribution with a parameter p and it is expressed as X
Here by taking q =1 − p
P ( x ) = P ( X = x ) = p x q1− x ; x = 0, 1
Here p + q = 1
Mean
Mean of the Bernoulli distribution E ( X )
E (X ) = p
Variance
Variance of the Bernoulli distribution Var ( X )
Var ( X ) = p(1 − p )
Binomial Distribution
If a random experiment consists of only two outcomes is conducted for more than once, one turn of such
an experiment is known as a binomial trial.
2
January, 2023
Handout No. - 6 HPD-DS
In order that a random variable X which is defined in connection with a binomial experiment, the
following four conditions, should be satisfied by X to have a bi normal distribution
Probability Function
The probability that the random variable X – which satisfies those four conditions, taking a value of X
is defined as
n− x
P ( x ) = P ( X = x ) = nC x p x (1 − p ) ; x = 0, 1, 2, ,n
P ( x ) = P ( X = x ) = nC x p x q n− x ; x = 0, 1, 2, ,n
Thereby, X is a random variable having a binomial distribution with parameters n and p, it is denoted
as, X Bin (n, p ) .
Mean
Mean of the Binomial distribution, E ( X )
E(X ) = n p
Variance
Variance of the Binomial distribution, Var ( X )
Var ( X ) = n p q
A binomial distribution whose P = 0.5 is symmetrical where as a binomial distribution with P 0.5 is
right skewed and a binomial distribution with P 0.5 is left skewed.
Example 1: Doctors states that the success rate of a surgery is 70%. If 5 patients are admitted to certain
hospital in a certain month, find,
i. The probability of getting exactly three surgeries successful.
ii. The probability of getting one surgery successful.
3
January, 2023
Handout No. - 6 HPD-DS
Example 3: In an examination, a paper consists of 3 0multiple choice questions with 5 choices. Find the
probability of answering 5 or more than questions correctly.
Example 4: According the past records, it is revealed that 10% of the manufactured iron nails are
defectives. If 5 iron nails are randomly selected from the machine, find the probability that,
Example 5: The past records of a certain bulb manufacturing company indicates that 10% of the
manufactured bulbs are defectives. If a person purchases 8 light bulbs, find the probability
that,
i. Non is defective
ii. At least three are defective
iii. At least one is defective
iv. Find the mean and the variance of the defective bulbs.
4
January, 2023
Handout No. - 6 HPD-DS
Poisson Distribution
The theoretical probability model that has been developed to solve the probability-based problems
related to discrete random variables which are distributed throughout time and/or space is known as
the ‘Poisson distribution’.
For examples, the number of typos on a printed page, the number of cars passing through the
intersection of Allen Street and College Avenue in one minute, the number of customers at an ATM in
10-minute intervals, the number of students arriving during office hours can be stated. Since each of
these situations are random, they are assumed to be distributed in Poisson distributions.
Probability Distribution
e− x
P ( x) = P ( X = x) = ; x = 0, 1, 2, ,n,
x!
is known as the probability mass function of a Poisson distribution.
is the mean of the Poisson distribution and e is a constant ( e = 2.71828)
The above probability mass function of the Poisson distribution has been developed based on
following assumptions.
i. The events occurred in a particular time interval / in an area of space are independent from the
events occurred in another time interval/ in an area of space which are not intersected on one
another.
ii. Probability of occurring the events in a particular time interval or in an area of space is
proportionate to the length of that time interval or the area of the space.
iii. The probability of occurring two or more events in a too tiny interval or in a very small space is
ignorably small.
Mean
Mean of the Poisson distribution, E ( X ) =
Variance
Variance of the Poisson distribution, Var ( X ) =
Example 1 : The average number of customers coming to a bank in an hour has been experienced as 24.
It takes 10 minutes time for one customer to get his work done in the bank. Find the
probability that.
i. no any customer coming
ii. two customers coming
iii. at least three customers coming
5
January, 2023
Handout No. - 6 HPD-DS
for n becomes larger, that is when n → and when the value of p becomes smaller, that is when the
value of p close to 0 ( p → 0) , and mean of the binomial distribution is less than 5 ( np 5 ) , the binomial
n− x e− x
n
C x p x (1 − p ) (Here = np )
x!
Example 1 : By taking n = 1000 and p = 0.001 of a random variable X, find the following probabilities
Example 2 : in a certain factory, 5% of the manufactured items are defectives. If 10 products were taken
randomly find the probability of having exactly two defectives by using
i. Binomial distribution
ii. Poisson distribution
Example 3 : In a certain iron nail manufacturing company, 5% of the manufactured iron nails are
defectives. If a sample of 200 iron nails are taken randomly, find the probability of
6
January, 2023
Handout No. - 6 HPD-DS
7
January, 2023