Download as pdf or txt
Download as pdf or txt
You are on page 1of 10

Segment: Discrete Distributions - Part I

Topic 1: Binomial Distribution

Topic 2: Properties of a Binomial Distribution

Topic 3: Mean and Variance


DISCRETE DISTRIBUTIONS - PART I

Hello, I am Dr. Ganesh C. B, welcome to this video on discrete distributions.

In this video, we will cover three topics. The first topic is binomial distribution. In this topic,
we will explore the definition of binomial distribution and binomial probability function. In
the second topic, we will explore the properties of binomial distribution. This will involve
identifying binomial random variables. In the third topic, we will explore mean and variance.

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 2/10
DISCRETE DISTRIBUTIONS - PART I

This will involve mean, variance, and standard deviation. Let us look at these topics in-depth
to gain a better understanding of discrete distributions.

Let us first look at the learning objectives of this session.

At the end of this video, you will be able to:

• Define binomial random variables


• Explain real-world situations using binomial distributions

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 3/10
DISCRETE DISTRIBUTIONS - PART I

Topic 1: Binomial Distribution

Suppose an experiment has been done with 𝑛 trials, considering 𝑥 as the number of
successes occurring in 𝑛 trials out of two possible outcomes that is success or failure,
where 𝑥 will be the binomial random variable.

Consider an experiment for Binomial random variable (RV): the number of tails in three
successive coin tosses. This experiment has only two possible outcomes at one toss that
is, either of getting head or tail where getting tail represents success and getting head
represents failure.

The outcome possibilities of this experiment are as given below:


TTT, THH, HTH, HHT, TTH, THT, HTT, HHH

Here, we got altogether 8 possibilities in this experiment, where HHH has the number of
outcomes (success in getting tail) is equal to 0. THH, HTH, HHT has the number of
outcomes is equal to 1. TTH, THT, HTT has the number of outcomes (success in getting tail)
is equal to 2 and TTT has the number of outcomes (success in getting tail) is equal to 3. So,
the possible values that can be taken by 𝑥 are 0, 1, 2, 3. In this experiment, the maximum
number of values of getting tail, that can be taken by 𝑥 is 3 and the minimum value can be

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 4/10
DISCRETE DISTRIBUTIONS - PART I

taken as 0. Out of the three-coin tosses, the maximum number of tails that you can get is 3
and the minimum number of tails that you can get is 0. In this case, 𝑥 is a discrete random
variable which represents the number of tails out of the three-coin tosses. The values of 𝑥
are represented as the corresponding probability that is 𝑓𝑥.

So, the values of 𝑥 will be represented as binomial probability function that is 𝑓𝑥 is given as,
𝑛!
𝑓(𝑥) = 𝑝 𝑥 (1 − 𝑝)(𝑛−𝑥)
𝑥! (𝑛 − 𝑥)!
𝑛!
Where, represents the number of experimental outcomes providing exactly 𝑥
𝑥!(𝑛−𝑥)!

successes in 𝑛 trials and 𝑝 𝑥 (1 − 𝑝)(𝑛−𝑥) represents the probability of a particular sequence


of trial outcomes with 𝑥 successes in 𝑛 trials where 𝑝 represents the probability of success
of getting tails with a fair toss. So, 𝑝 = 0.5. As it has been already mentioned that coin will
𝑛 3
be tossed 3 times, so 𝑛 = 3. Finding the probability of 𝑥 = 0. 𝑐 denotes 𝑐 which is 1. 𝑝 𝑥
0 0
denotes (0.5)0 which is 1. (1 − 𝑝)(𝑛−𝑥) denotes (1 − 0.5)(3) which is equal to (0.5)3 which is
1 1 1
equal to (2)3 which is equals to 8. So, the probability of 𝑥 while taking the value 0 is .
8

Similarly, the Binomial probability function of 𝑥 taking the values 1, 2, 3 will also be found.

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 5/10
DISCRETE DISTRIBUTIONS - PART I

Topic 2: Properties of Binomial Distribution

Following are the properties of a binomial distribution which will help in identifying whether
a random variable will satisfy to be a binomial random variable or not:

1) The experiment consists of a sequence of 𝑛 identical trials.


2) Two outcomes, success, and failure are possible in each trial.
3) The probability of success, denoted by 𝑝, does not change from trial to trial.
4) The trials are independent.

To check whether the above-mentioned conditions are satisfying or not, condition 1 states
that the experiment consists of a sequence of 𝑛 identical trials. As in the previous example,
we had three-coin tosses, so 𝑛 = 3, and coin tosses are identical. So, it will satisfy condition
1. In condition 2, there should be only two outcomes, either success or failure. In each coin
toss, there are only two outcomes, either a tail or a head where tail means success and head
mean failure, so it will satisfy condition 2 as well. The third condition states that the
probability of success denoted by 𝑝, should not change from trial to trial. Our example with
the success of coin toss means getting a tail and the probability of getting tails in a fair coin
1
is 2 and that does not change from coin toss 1 to coin toss 2. So, it satisfies condition 3. In

condition 4, the trial should be independent. In our previous example, we had three

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 6/10
DISCRETE DISTRIBUTIONS - PART I

independent coin tosses and hence it also satisfies condition 4 as well. So, if these four
conditions are satisfied. We can conclude that the random variable is a binomial random
variable, and the binomial probability function can be used to find the probability of that
random variable taking any particular value.

Topic 3: Mean and Variance of a Binomial Distribution

Now in the third topic, we will discuss mean, variance, and standard deviation.
The mean or the expected value of 𝑥 is also represented as 𝜇 as given in the formula,
𝐸(𝑥) = 𝜇 = 𝑛𝑝
So, for the coin toss example, 𝑛 = 3 as there were three-coin tosses and 𝑝 = 0.5, which is
the probability of success (getting tails in outcome). So, the expected value of 𝑥 that is 𝐸(𝑥)
will be 3 × 0.5 which is equal to 1.5. The expected number of times, tails came as outcome
in this example will be 1.5.

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 7/10
DISCRETE DISTRIBUTIONS - PART I

Now, the variance of 𝑥 is represented using Sigma square (𝜎 2 ) and it is given by the formula,
𝑛𝑝(1 – 𝑝)
that is,
𝑉𝑎𝑟(𝑥) = s2 = 𝑛𝑝(1 – 𝑝)
As the number of trials was 3 that is 𝑛 = 3, and counting was done to the number of tails in
three-coin tosses and 𝑝 is the probability of success, which is essentially the probability of
getting a tail is 𝑝 = 0.5. Here, 1 – 𝑝 will be 1 – 0.5 which is equal to 0.5 again. So, the variance
of 𝑥 which is also represented as 𝑉𝑎𝑟(𝑥) or Sigma square 𝜎 2 is equal to 3 × 0.5 × 0.5 which
is equal to 3 × 0.25 which is equal to 0.75.

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 8/10
DISCRETE DISTRIBUTIONS - PART I

Now, if the variance is known to us then we can also find the standard deviation. So, in this
case, the variance 𝜎 2 = 0.75. So, the standard deviation Sigma (𝜎) will be given by √0.75.

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 9/10
DISCRETE DISTRIBUTIONS - PART I

Summary

In this topic, we discussed:

• Binomial distribution and binomial probability function


• Identifying a binomial random variable
• Mean and variance of binomial distribution

©COPYRIGHT 2023 (VER. 1.0), ALL RIGHTS RESERVED. MANIPAL ACADEMY OF HIGHER EDUCATION 10/10

You might also like