1

Contents
Random Variables – An Introduction ....................................................................................................... 4
Unit – I .................................................................................................................................................... 5
Probability Distribution................................................................................................................................................. 5
Probability Distribution: ........................................................................................................................................................................................................... 5
Properties of Probability Mass Function:................................................................................................................................................................................. 5
Various Representations of Discrete Random Variables: ........................................................................................................................................................ 6
Expectation and Variance of Probability Distribution: ............................................................................................................................................................ 9

Unit – II ................................................................................................................................................. 13
Binomial Distribution ...................................................................................................................................................13
Binomial Distribution: ............................................................................................................................................................................................................ 13
Conditions for Binomial Distribution: .................................................................................................................................................................................... 13
Bernoulli’s Trials: .................................................................................................................................................................................................................... 14
Definition of Binomial Distribution: ....................................................................................................................................................................................... 15
Probability Mass Function of Binomial Distribution: ............................................................................................................................................................. 15
Representation of Probability Mass Function: ...................................................................................................................................................................... 15
Using Probability Mass Function to find Cumulative Probabilities: ....................................................................................................................................... 16
Expectation and Variance of Binomial Distribution: .............................................................................................................................................................. 17

Unit – III ................................................................................................................................................ 22

Geometric Distribution ................................................................................................................................................22
Geometric Distribution: ......................................................................................................................................................................................................... 22
Conditions for Geometric Distribution: ................................................................................................................................................................................. 22
Definition of Geometric Distribution: .................................................................................................................................................................................... 22
Probability Mass Function of Geometric Distribution: .......................................................................................................................................................... 22
Representation of Probability Mass Function: ...................................................................................................................................................................... 23
Using Probability Mass Function to find cumulative probabilities: ....................................................................................................................................... 23
Expectation of Geometric Distribution: ................................................................................................................................................................................. 24

Unit – IV................................................................................................................................................ 27
Normal Distribution .....................................................................................................................................................27
Normal Distribution: .............................................................................................................................................................................................................. 27
Definition of Normal Distribution: ......................................................................................................................................................................................... 27
Probability Density Function of Normal Distribution:............................................................................................................................................................ 27
Representation of Probability Density Function of Normal Distribution: ............................................................................................................................. 28
Properties of Normal Distribution Curves: ............................................................................................................................................................................ 28
Effect of Mean in Normal Distribution Curves: ...................................................................................................................................................................... 29
Effect of Standard Deviation in Normal Distribution Curves: ................................................................................................................................................ 29
Standard Normal Distribution: ............................................................................................................................................................................................... 30
Need of Standard Normal Distribution: ................................................................................................................................................................................. 30
Normal Distribution Table: .................................................................................................................................................................................................... 31
Rules for using the Normal Distribution Table:...................................................................................................................................................................... 32
Summary of Rules for using the Normal Distribution Table: ................................................................................................................................................. 39
Application of Normal Distribution to Find Probabilities:...................................................................................................................................................... 40
Finding 𝒛 value from the given probability: ........................................................................................................................................................................... 42
Summary of rules for finding the 𝒛 value from the probability: ............................................................................................................................................ 45
Binomial to Normal Approximation: ...................................................................................................................................................................................... 49
Continuity Correction:............................................................................................................................................................................................................ 50
Problems involving Binomial and Normal Distribution:......................................................................................................................................................... 55

Answers ................................................................................................................................................ 57
Module Summary ................................................................................................................................. 62

2
3
 Random Variables – An Introduction
Random Variables:
Let’s learn about random variables through an example.
Say, a die is rolled two times and the expected outcome is getting 3. Now, there are three possibilities:
Possibility 1: Not getting 3 in both the attempts, that is, the number of three’s occurred is 0.
Possibility 2: Getting 3 in one of the two attempts, that is, the number of three’s occurred is 1.
Possibility 3: Getting 3 in both the attempts, that is, the number of three’s occurred is 2.
The numerical values of these possibilities (0, 1, 2) are set to a variable which is known as a random variable.
Say, the variable 𝑋 can take values such that 0 ≤ 𝑋 ≤ 2, then 𝑋 is the random variable of the above
experiment.
The values of a random variable depend on the probability of each outcome.

Types of Random Variables:

There are two types of random variables:
▶ Discrete random variables
▶ Continuous random variables

Discrete Random Variables:

A discrete random variable only takes values which can be counted. The example discussed above, of rolling
a die twice and expecting 3 as an outcome, is a perfect example of discrete random variables.

Continuous Random Variables:

Random variables which can take an infinite number of possibilities are called continuous random variables.
All measurable quantities come under continuous random variables.
For example, heights of class 12 students can have infinite possibilities within a wide range.
In this module we will learn:
➢ Probability Distribution
➢ Binomial Distribution
➢ Geometric Distribution
under discrete random variables and
➢ Normal Distribution
under continuous random variables.

4
 Unit – I
Probability Distribution
Probability Distribution:
Representing the values of random variables of a particular event along with the probability of its occurrence
in the form of a table is known as probability distribution.
Let’s take the same example which we discussed in the previous page to explain probability distribution.
Say, a die is rolled two times and the expected outcome is getting 3.
The random variable 𝑋 takes the values 0, 1 and 2.
Now, let’s find the probability for each possibility of 𝑋 values.
For 𝑋 = 0, we don’t get three’s in both throws. Hence,
5 5 25
𝑃(𝑋 = 0) = 𝑃(3̅, 3̅) = × =
6 6 36
For 𝑋 = 1, we get only one three in two throws. The three can occur either in the first throw or in the second
throw. Hence,
1 5 5 1 10
𝑃(𝑋 = 1) = 𝑃(3, 3̅) + 𝑃(3̅, 3) = × + × =
6 6 6 6 36
For 𝑋 = 2, we get three’s in both the throws. Hence,
1 1 1
𝑃(𝑋 = 2) = 𝑃(3,3) = × =
6 6 36
The probability distribution table for the above example is given below:

𝒙 0 1 2

25 10 1
𝑷(𝑿 = 𝒙)
36 36 36

Here, the probability function 𝑷(𝑿 = 𝒙) is known as a Probability Mass Function (PMF).

Properties of Probability Mass Function:

▶ The value of 𝑃(𝑋 = 𝑥 ) lies between 0 and 1, that is, 𝟎 ≤ 𝑷(𝑿 = 𝒙) ≤ 𝟏.
▶ The sum of all the probabilities equals to 1, that is, ∑𝑷(𝑿 = 𝒙) = 𝟏.
From the above example,
25 10 1 36
∑𝑃(𝑋 = 𝑥 ) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) = + + = =1
36 36 36 36

5
Various Representations of Discrete Random Variables:
Apart from a probability distribution table, there are two other ways of representing discrete random
variables, which we will learn now.
The following diagram illustrates the representation of probability mass function as lines:

The horizontal line is labelled with the values of random variables.

The height of each vertical line represents the probability of the particular random variable.
The following diagram illustrates the representation of probability mass function as bars.

The horizontal line is labelled with the values of random variables.

The height of each bar represents the probability of the particular random variable while the width of each bar
is one unit. Hence, the area of each bar is equal to the probability of that particular random variable.
The value of the random variable is labelled at the middle of the width of each bar. The values of each bar
ranges from 𝑅. 𝑉 − 0.5 to 𝑅. 𝑉 + 0.5, where 𝑅. 𝑉 is the random variable. For example, the width of the bar of
random variable 1 ranges from 0.5 to 1.5.

6
Example I – 1: A fair die has one face numbered 𝟐, two faces numbered 𝟑, one face numbered 𝟒 and
two faces numbered 𝟔. The die is thrown twice. Let 𝑿 be the sum of the two scores.
(i) Draw a table showing the probability distribution of 𝑿.
(ii) Find the probability that 𝑿 is greater than 𝟖.
(iii) Find 𝑷(𝟓 < 𝑿 ≤ 𝟗).
(i) A two-way table can make finding the probabilities easier in this case.

First die
+ 𝟐 𝟑 𝟑 𝟒 𝟓 𝟓
𝟐 4 5 5 6 7 7
𝟑 5 6 6 7 8 8
Second die

𝟑 5 6 6 7 8 8
𝟒 6 7 7 8 9 9
𝟓 7 8 8 9 10 10
𝟓 7 8 8 9 10 10

From the table, the possible outcomes are 4, 5, 6, 7, 8, 9, 10.

Hence, 𝑋 can take values from 4 to 10. Since we can read the probabilities for each value of 𝑋 from the
two-way table, we can directly draw the probability distribution table as follows.

𝒙 4 5 6 7 8 9 10

1 4 5 8 9 4 4
𝑷(𝑿 = 𝒙)
36 36 36 36 36 36 36

(ii)
𝑃(𝑋 > 8) = 𝑃(𝑋 = 9) + 𝑃(𝑋 = 10)
4 4 8 2
= + = =
36 36 36 9
(iii)
𝑃(5 < 𝑋 ≤ 9) = 𝑃(𝑋 = 6) + 𝑃(𝑋 = 7) + 𝑃(𝑋 = 8) + 𝑃(𝑋 = 9)
5 8 9 4 4 5
= + + + + =
36 36 36 36 36 6
Example I – 2: The probability distribution of the discrete random variable 𝑿 is shown in the table
below.

𝒙 0 1 3 6

𝑷(𝑿 = 𝒙) 𝑝 2𝑝 0.2𝑞 0.6𝑞

It is given that 𝒑 + 𝟒𝒒 = 𝟏. 𝟓. Find the values of 𝒑 and 𝒒.

7
We know that, ∑𝑃(𝑋 = 𝑥 ) = 1. Hence,
𝑝 + 2𝑝 + 0.2𝑞 + 0.6𝑞 = 1
3𝑝 + 0.8𝑞 = 1
It is also given that 𝑝 + 4𝑞 = 1.5.
Solving both equations simultaneously, we get
1 5
𝑝 = ;𝑞 =
4 16
Exercise I – 1
210
1. In a particular discrete probability distribution the random variable 𝑋 takes the value with
𝑠
𝑠
probability , where 𝑠 takes all integer values from 1 to 10 inclusive.
55
(i) Construct the probability distribution table for 𝑋.
(ii) What is the modal value of 𝑋?
(iii) Find the probability that 𝑋 lies between 35 and 70 inclusive.
2. In a probability distribution, the random variable 𝑌 takes the value 𝑦 with probability 𝑏𝑦, where 𝑦 takes
values 1, 2, 3, 4, 5, 6 only. Draw a probability distribution table for 𝑌, in terms of 𝑏, and find the value
of 𝑏.
3. Lucia and Lucas play a game using a fair 5 – sided spinner numbered 2, 5, 6, 7, 9. Lucia spins the
spinner and notes down the number on which the spinner is landed. Then, Lucas spins the spinner and
notes down the number on which the spinner is landed. If their two numbers are equal the score is zero.
Otherwise, the smaller number is subtracted from the larger number to give the score.
(i) Draw up a probability distribution table for the score.
If the score is 0 they play again. If the score is 4 or more, Lucia wins. Otherwise, Lucas wins. They
continue playing until one of the players wins.
(ii) Find the probability that Lucia wins with the second spinning.
(iii) Find an expression for the probability that Lucia wins on the 𝑛th spin.
4. A box contains 4 green cards and 6 blue cards. Martin takes 3 of these cards at random, without
replacement. Draw a probability distribution table for the number of blue cards Martin takes.
5. A fair tetrahedral die, numbered 1, 2, 3 and 4, is thrown three times and the number on the face the die
lands on is noted. The random variable 𝑋 is the sum of the three scores. Draw a probability distribution
table for 𝑋.
6. Sofia has a bag of balls containing 6 red balls and 3 blue balls. Daniel has a bag of balls containing 4
red balls, 5 blue balls and 3 green balls. A ball is taken at random from Sofia’s bag and put in Daniel’s
bag. A ball is then taken at random from Daniel’s bag. The random variable 𝑋 is the number of times a
red ball is taken. State the possible values of 𝑋 and draw a table to show the probability distribution of
𝑋.
7. Punit has a fair coin and a fair six-sided die numbered 1, 2, 3, 4, 5 and 6. He tosses the coin once and
the die twice. The random variable 𝑋 is defined as follows.
➢ If the coin lands on heads then 𝑋 is the sum of the scores on the two throws of the die.
➢ If the coin lands on tails then 𝑋 is the score on the first throw of the die only.
Draw a probability distribution table for 𝑋.

8
8. Nancy has 12 cards. Seven of the cards have a 4 printed on them and five of the cards have a 5 printed
on them. She takes three cards at random, without replacement, and adds up the numbers on the cards.
Draw a probability distribution table for the sum of the numbers on the three cards.
9. Arya chooses two digits at random, without replacement, from the 10 − digit number
1 2 2 3 3 3 4 4 4 4.
(i) Find the probability that the two digits chosen are equal.
(ii) Find the probability that the first digit Arya chose was a 3, given that the second digit he chose is
not a 3.
(iii) The random variable 𝑋 is the number of 4’s that Arya chooses. Draw a table to show the probability
distribution of 𝑋.
10. Ajay throws a biased six-sided die numbered 1, 2, 3, 4, 5 and 6. The score is the number on the face the
die lands on. The score is denoted by the random variable 𝑋, which has the probability distribution
shown in the table.

𝒙 1 2 3 4 5 6

𝑷(𝑿 = 𝒙) 0.1 2𝑝 0.25 3𝑝 0.15 0.125

(i) Find the value of 𝑝.

His friend Anu throws a biased tetrahedral die numbered 1, 2, 3, 4. The score when this die is thrown is
denoted by the random variable 𝑌. It is given that 𝑃(𝑌 = 1) = 0.2, 𝑃(𝑌 = 2) = 0.3, 𝑃(𝑌 = 3) = 0.4
and 𝑃(𝑌 = 4) = 0.1.
(ii) Find the probability that, when both dice are thrown together,
(a) the sum of the scores is 8,
(b) the product of the scores is less than 6.
11. The discrete random variable 𝑋 takes the values 1, 2, 3, 4 and 5 only. The probability distribution of 𝑋
is shown in the table.

𝒙 1 2 3 4 5

𝑷(𝑿 = 𝒙) 𝑝2 1.25𝑝 0.5𝑝 0.5𝑝2 0.75𝑝

Find 𝑝.

Expectation and Variance of Probability Distribution:

The mean value of the random variables of a probability distribution is known as the expectation of the
probability distribution. It is denoted as 𝑬(𝑿) or 𝝁.
If 𝑋 is a random variable that takes the values 𝑥1 , 𝑥2 , 𝑥3 , …, 𝑥𝑛 and their corresponding probabilities are 𝑝1 ,
𝑝2 , 𝑝3 , …, 𝑝𝑛 , then the expectation of the probability distribution of 𝑋 is
𝐸 (𝑋) = 𝑥1 𝑝1 + 𝑥2 𝑝2 + 𝑥3 𝑝3 + ⋯ + 𝑥𝑛 𝑝𝑛

𝑬(𝑿) = ∑𝒙𝒑
When we discuss the mean, it is necessary to find the standard deviation also. The square of standard deviation
is known as variance, which is denoted as 𝑽𝒂𝒓(𝑿) or 𝝈𝟐 .

9
Variance of the above data can be calculated as
2
𝑉𝑎𝑟(𝑋) = 𝑥12 𝑝1 + 𝑥22 𝑝2 + 𝑥32 𝑝3 + ⋯ + 𝑥𝑛2 𝑝𝑛 − (𝐸 (𝑋))
𝟐
𝑽𝒂𝒓(𝑿) = ∑𝒙𝟐 𝒑 − (𝑬(𝑿))
Example I – 3: Sri throws a fair tetrahedral die with faces numbered 𝟏, 𝟐, 𝟑, 𝟒. If she gets an odd
number, she throws again and her score is the sum of both numbers obtained. If she gets an even
number, she throws again and her score is the absolute value of the difference of both numbers obtained.
Let the random variable 𝑿 denote Sri’s score. Calculate 𝑬(𝑿) and 𝑽𝒂𝒓(𝑿).
A two-way table can make finding the probabilities easier in this case.

Second die
+ 𝟏 𝟐 𝟑 𝟒
𝟏 2 3 4 5
First die

𝟐 1 0 1 2
𝟑 4 5 6 7
𝟒 3 2 1 0

From the table, the possible outcomes are 0, 1, 2, 3, 4, 5, 6, 7.

Hence, 𝑋 can take values from 0 to 7. Since we can read the probabilities for each value of 𝑋 from the
two-way table, we can directly draw the probability distribution table as follows.

𝒙 0 1 2 3 4 5 6 7

2 3 3 2 2 2 1 1
𝑷(𝑿 = 𝒙)
16 16 16 16 16 16 16 16

2 3 3 2 2 2 1 1
Expectation, 𝐸 (𝑋) = 0 × +1× +2× +3× +4× +5× +6× +7×
16 16 16 16 16 16 16 16
23
𝐸 (𝑋) = = 2.875
8

2
2 2
3 2
3 2
2 2
2 2
2 2
1 2
1 23 2
𝑉𝑎𝑟 (𝑋) = 0 × +1 × +2 × +3 × +4 × +5 × +6 × +7 × −( )
16 16 16 16 16 16 16 16 8
271
𝑉𝑎𝑟(𝑋) = = 4.23
64

Exercise I – 2
1. Alex’s two-wheeler has trouble starting. Every time he tries to start the vehicle, there is a 60% chance
that it will start. If his vehicle starts, he will go to his office in his two-wheeler. If his vehicle does not
start, Alex tries again in a few minutes’ time. If his vehicle has not started after 4 attempts, Alex goes to
the office in his car.
(i) Let 𝑋 be the number of times Alex’s two-wheeler does not start in a day. Draw up a table to show
the probability distribution of 𝑋. A tree diagram might help to find the probabilities.
(ii) Calculate the expected number of times the two-wheeler does not start on that day.

10
2. A pet shop has 6 Poodles and 3 German Shepherd puppies. Amar selects four of these puppies at random.
The random variable 𝑋 represents the number of German Shepherd puppies chosen.
(i) Draw up the probability distribution of 𝑋.
(ii) Find 𝐸 (𝑋) and 𝑉𝑎𝑟(𝑋).
3. Aashi has ten cards, in which five cards are numbered 0, two cards are numbered 3 and three cards are
numbered 5.
Tenzin has eight cards, in which five cards are numbered 0 and three cards are numbered 3.
One card is selected from each of them. The random variable 𝑋 is defined as the sum of the numbers on
these two cards.
(i) Tabulate the probability distribution of 𝑋.
(ii) Find 𝐸 (𝑋) and 𝑉𝑎𝑟(𝑋).
(iii) Given that 𝑋 = 3, find the probability that the card chosen from Aashi was numbered 3.
4. A wood-cutting machine cut pieces of wood with large diameters, of lengths either 2 m or 4 m. There
are five times as many pieces of wood of length 2 m as there are pieces of wood of length 4 m.
(i) One piece of wood is chosen at random. Find the expectation and variance of its length.
(ii) Two pieces of wood are chosen at random. Find the probability that they have different lengths.
(iii) Three pieces of wood are chosen at random. Find the probability that their total length is 10 m.
5. The six faces of a fair die are numbered 1, 2, 2, 2, 3 and 4. The score for a throw of the die, denoted by
the random variable 𝑌, is the number on the top face after the die has landed. Find the mean and standard
deviation of 𝑌.
6. The random variable 𝑋 has the probability distribution shown in the table.

𝒙 1 3 5

𝑷(𝑿 = 𝒙) 0.3 0.2 0.5

Two independent values of 𝑋 are chosen at random. The random variable 𝑊 takes the value 0 if the two
values of 𝑋 are the same. Otherwise, the value of 𝑊 is the larger value of 𝑋 minus the smaller value of
𝑋.
(i) Draw the probability distribution table for 𝑊.
(ii) Find the expected value of 𝑊.
7. The probability distribution of the random variable 𝑋 is shown in the following table.

𝒙 −3 −1 0 1 3 5

𝑷(𝑿 = 𝒙) 0.05 𝑝 0.3 𝑞 0.15 0.1

The mean of 𝑋 is 0.9.

(i) Find the values of 𝑝 and 𝑞.
(ii) Find the variance of 𝑋.

11
8. The probability distribution of the discrete random variable 𝑋 is shown in the following table.

𝒙 −2 −1 0 2 3

𝑷(𝑿 = 𝒙) 𝑎 0.2 0.3 0.18 𝑏

Given that 𝐸 (𝑋) = 0.12, find the values of 𝑎 and 𝑏.

9. The possible values of the random variable 𝑋 are the 7 integers in the set {−3, −2, −1, 0, 1, 2, 3,4}. The
probabilities of 𝑋 values in the set {−2, 0, 2, 4} are all equal and equals to twice the probabilities of 𝑋
values in the set {−3, −1, 1, 3} which are also equal. Calculate
(i) 𝐸 (𝑋),
(ii) 𝑃(𝑋 < 𝐸 (𝑋)),
(iii) the value of 𝑐 for which 𝑃(−𝑐 ≤ 𝑋 ≤ 2𝑐) = 0.5.
10. The discrete random variable 𝑋 has the following probability distribution.

𝒙 −2 0 2 4

𝑷(𝑿 = 𝒙) 𝑎 𝑏 𝑐 0.1

Given that 𝐸 (𝑋) = 0.8 and 𝑉𝑎𝑟(𝑋) = 3.36, find the values of 𝑎, 𝑏 and 𝑐.

12
 Unit – II
Binomial Distribution
Binomial Distribution:
Binomial distribution is an example of discrete random variables. Binomial distribution is used for events
which only have two possible outcomes. Hence, it is called as ‘binomial’.
Few examples are:
1. Throwing a die 10 times and expecting a six as an output (so, the possible outcomes are either 𝟔
or not 𝟔).
2. Number of defective products in a box of 20 products (so, the possible outcomes are either a
defective product or a non-defective product)
For these events, the expected outcome is called ‘success’ and the other outcome is called ‘failure’.
For the first event, success is getting a 𝟔 and failure is not getting a 6.
For the second event, success is getting a defective product and failure is not getting a defective product.

Conditions for Binomial Distribution:

1. A fixed number (𝒏) of trials take place.
For example:
a. Throwing a die 𝟏𝟎 times.
b. Tossing a coin 𝟐𝟎 times.
c. Taking balls from a bag of 𝟏𝟎 balls.
2. A single trial has exactly two possible outcomes (success and failure) and these are mutually
exclusive.
For example:
a. Throwing a die 10 times and expecting an even number (success – even; failure – odd).
b. Tossing a coin 20 times and expecting heads (success – heads; failure – tails).
c. Taking a red ball from a bag of 10 balls which contains 6 red and 4 green balls (success – red ball;
failure – not a red ball).
3. The outcome of each trial is independent of the outcome of all the other trials.
For example:
a. Getting an even number in the first throw of a die will not affect the outcome of the second throw
of the die.
b. Getting an outcome when tossing a coin any number of times is independent for each coin toss.
c. Picking up balls from a bag containing 𝑛 balls is independent if the ball chosen is getting replaced
in the bag continuously.
4. The probability of success at each trial is constant.
For example:
1
a. The probability of getting an even number is constant (= ) for any number of times the die is
2
thrown.
1
b. The probability of getting a head is always constant (= ) for any number of times the coin is
2
tossed.

13
Bernoulli’s Trials:
Swiss mathematician Jakob Bernoulli determined that the probability of 𝑟 outcomes in 𝑛 trials is equal to the
𝑟th term (𝑟 = 0, 1, 2, 3, … , 𝑛) in the expansion of the binomial expression (𝒒 + 𝒑)𝒏 , where 𝑝 is the probability
of success and 𝑞 is the probability of failure.
Let’s understand the above statement through an example.
A deck of 𝟐𝟎 cards contains 𝟖 cards with a picture of a 𝒍𝒊𝒐𝒏 printed on it and 𝟏𝟐 cards with a picture
of a 𝒕𝒊𝒈𝒆𝒓 printed on it. Raju picks up 𝟓 cards randomly from the deck of cards with replacement. Let
𝑿 be a random variable which denotes the number of cards with a 𝒍𝒊𝒐𝒏 printed on it.
𝑋 takes the values 0, 1, 2, 3, 4, 5.
𝑃(𝑋 = 0) = 𝑃(all five cards don′ t have a 𝑙𝑖𝑜𝑛 printed on it)
12 12 12 12 12 12 5
= 𝑃(𝐿̅, ̅𝐿, ̅𝐿, 𝐿̅, 𝐿̅) = × × × × =( )
20 20 20 20 20 20
8 12 12 12 12 5! 5 8 12 4
𝑃(𝑋 = 1) = 𝑃(𝐿, ̅𝐿, ̅𝐿, 𝐿̅, 𝐿̅) = × × × × × = ( )( )( )
20 20 20 20 20 1! 4! 1 20 20
5! 5!
We are multiplying it with because Raju may have the cards 𝐿, ̅𝐿, ̅𝐿, 𝐿̅, 𝐿̅ in any order, and equals to
1!4! 1!4!
5
the value of 5𝐶1 or ( ).
1
8 8 12 12 12 5! 5 8 2 12 3
𝑃(𝑋 = 2) = 𝑃(𝐿, 𝐿, ̅𝐿, 𝐿̅, 𝐿̅) = × × × × × = ( )( ) ( )
20 20 20 20 20 2! 3! 2 20 20
8 8 8 12 12 5! 5 8 3 12 2
𝑃(𝑋 = 3) = 𝑃(𝐿, 𝐿, 𝐿, 𝐿̅, 𝐿̅) = × × × × × = ( )( ) ( )
20 20 20 20 20 3! 2! 3 20 20
8 8 8 8 12 5! 5 8 4 12
𝑃(𝑋 = 4) = 𝑃(𝐿, 𝐿, 𝐿, 𝐿, 𝐿̅) = × × × × × = ( )( ) ( )
20 20 20 20 20 4! 1! 4 20 20
8 8 8 8 8 8 5
𝑃(𝑋 = 5) = 𝑃(𝐿, 𝐿, 𝐿, 𝐿, 𝐿) = × × × × =( )
20 20 20 20 20 20
In this example, Raju is selecting 5 cards. Hence, 𝒏 = 𝟓. Success is getting a card with a 𝑙𝑖𝑜𝑛 printed on it.
𝟖 𝟏𝟐
Hence, the probability of success is 𝒑 = and the probability of failure is 𝒒 = .
𝟐𝟎 𝟐𝟎

Let’s now try to expand (𝑞 + 𝑝)𝑛 using binomial theorem.

12 8 5
(𝑞 + 𝑝 )𝑛 =( + )
20 20
12 5 5 8 12
4
5 8
2
12 3 5 8
3
12 2 5 8
4
12 8 5
= ( ) + ( )( )( ) + ( )( ) ( ) + ( )( ) ( ) + ( )( ) ( ) + ( )
20 1 20 20 2 20 20 3 20 20 4 20 20 20
Now, comparing the terms of these expansion with the probabilities calculated before, we get
(𝒒 + 𝒑)𝒏 = 𝑷(𝑿 = 𝟎) + 𝑷(𝑿 = 𝟏) + 𝑷(𝑿 = 𝟐) + 𝑷(𝑿 = 𝟑) + 𝑷(𝑿 = 𝟒) + 𝑷(𝑿 = 𝟓)
This is the relation explained by Bernoulli in 1713.
From the above conclusion, we can generalise the following:
𝒏
𝑷(𝑿 = 𝒓) = ( ) 𝒑𝒓 𝒒𝒏−𝒓
𝒓
where 𝑟 = 0, 1, 2, …, 𝑛.

14
Definition of Binomial Distribution:
From its conditions, it is evident that binomial distribution is dependent on the number of trials (𝑛) and the
probability of success (𝑝). Hence, 𝑛 and 𝑝 are the parameters of binomial distribution.
Therefore, binomial distribution is defined as

𝑿~𝑩(𝒏, 𝒑)
where 𝑿 is the random variable, 𝒏 is the number of trials and 𝒑 is the probability of success.
Since the events success and failure are mutually exclusive, their probabilities add up to 1.

𝒑+𝒒=𝟏
Probability Mass Function of Binomial Distribution:
The probability mass function of binomial distribution is given by:
𝒏
𝑷(𝑿 = 𝒙) = ( ) 𝒑𝒙 (𝟏 − 𝒑)𝒏−𝒙
𝒙
where 𝑥 = 0, 1, 2, …, 𝑛.
The probability mass function of binomial distribution also satisfies
𝒏

∑ 𝑷(𝑿 = 𝒙) = 𝟏
𝒙=𝟎

Representation of Probability Mass Function:

As for probability distribution, we can represent the probability mass function of binomial distribution in the
form of either a table, lines or bars.
Let’s represent the probability mass function of the example explained earlier in all three forms.
Tabular Form:

𝒙 0 1 2 3 4 5

𝑷(𝑿 = 𝒙) 0.07776 0.2592 0.3456 0.2304 0.0768 0.01024

Lines Form:

15
Bars Form:

Example II – 1: In a class, 𝟑𝟎% of the students opted for basketball, 𝟑𝟓% of the students opted for
football and remaining opted for volleyball. The teacher selected 𝟏𝟎 students from the class randomly.
Find the probability that the selected students consist of
(i) exactly three students who opted for basketball,
(ii) between 𝟒 and 𝟔 inclusive students who opted for football
(iii) more than 𝟑 students who opted for volleyball.
(i) In this question, 𝑛 = 10.
In this part, success is selecting a student who opted for basketball. Hence, 𝑝 = 0.3, 𝑞 = 0.7.
We are supposed to find 𝑃(𝑋 = 3).
10
𝑃(𝑋 = 3) = ( ) × 0.33 × 0.77 = 𝟎. 𝟐𝟔𝟕
3
(ii) Here, 𝑋~𝐵(10, 0.35).
𝑃(4 ≤ 𝑋 ≤ 6) = 𝑃(𝑋 = 4) + 𝑃(𝑋 = 5) + 𝑃(𝑋 = 6)
10 10 10
= ( ) × 0.354 × 0.656 + ( ) × 0.355 × 0.655 + ( ) × 0.356 × 0.654
4 5 6
= 0.2377 + 0.1536 + 0.0689 = 𝟎. 𝟒𝟔𝟎
(iii) Here also, 𝑋~𝐵(10, 0.35).
𝑃(𝑋 > 3) = 𝑃(𝑋 = 4,5,6,7,8,9,10)
= 1 − 𝑃(𝑋 = 0,1,2,3)
10 10 10
= 1 − {0.6510 + ( ) × 0.35 × 0.659 + ( ) × 0.352 × 0.658 + ( ) × 0.353 × 0.657 }
1 2 3
= 1 − {0.01346 + 0.07249 + 0.17565 + 0.25222} = 𝟎. 𝟒𝟖𝟔

Using Probability Mass Function to find Cumulative Probabilities:

From the above example, we can derive these results:

𝑷(𝑿 ≥ 𝒙) = 𝟏 − 𝑷(𝑿 < 𝒙)

𝑷(𝑿 > 𝒙) = 𝟏 − 𝑷(𝑿 ≤ 𝒙)

16
Expectation and Variance of Binomial Distribution:
As discussed for probability distribution, a random variable 𝑋 defined using binomial distribution also has a
mean/expectation and variance.
The following are the formulae to find expectation and variance of Binomial Distribution.
𝐄𝐱𝐩𝐞𝐜𝐭𝐚𝐭𝐢𝐨𝐧 𝒐𝒓 𝐌𝐞𝐚𝐧 = 𝑬(𝑿) = 𝒏𝒑
𝐕𝐚𝐫𝐢𝐚𝐧𝐜𝐞, 𝝈𝟐 = 𝒏𝒑𝒒 = 𝒏𝒑(𝟏 − 𝒑)
𝐒𝐭𝐚𝐧𝐝𝐚𝐫𝐝 𝐝𝐞𝐯𝐢𝐚𝐭𝐢𝐨𝐧, 𝝈 = √𝒏𝒑(𝟏 − 𝒑)

Example II – 2: A random variable 𝑿 is defined as 𝑿~𝑩(𝟏𝟓, 𝟎. 𝟐). Find

(i) 𝑷(𝑿 < 𝟐),
(ii) 𝑬(𝑿) and 𝑽𝒂𝒓(𝑿).
Here, 𝑛 = 15, 𝑝 = 0.2, 𝑞 = 0.8.
(i)
𝑃(𝑋 < 2) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1)
15
= 0.815 + ( ) × 0.2 × 0.814
1
= 0.03518 + 0.13194 = 𝟎. 𝟏𝟔𝟕
(ii) 𝐸 (𝑋) = 𝑛𝑝 = 15 × 0.2 = 𝟑
𝑉𝑎𝑟(𝑋) = 𝑛𝑝𝑞 = 15 × 0.2 × 0.8 = 𝟐. 𝟒
Example II – 3: The apple trees in a garden contains both good and rotten apples. It is found that the
average number of rotten apples in a tree 𝟐. 𝟖.
(i) Find the probability that among the 𝟐𝟎 apples plucked from a tree, the number of rotten apples
is greater than 𝟐.
Sumi randomly selected 𝟏𝟎 trees from the garden. 𝟐𝟎 apples were plucked from each of the selected
trees.
(ii) Find the probability that at least 𝟑 trees contain no rotten apples plucked from them.
(iii) Find the probability that at least 8 trees contain at most 2 rotten apples plucked from them.
(i) Here, average is given as 2.8 and 𝑛 = 20.
𝑛𝑝 = 2.8 ⇒ 20𝑝 = 2.8 ⇒ 𝑝 = 0.14
Hence, 𝑞 = 0.86.
𝑃(𝑋 > 2) = 1 − 𝑃(𝑋 ≤ 2)
20 20
= 1 − {0.8620 + ( ) × 0.14 × 0.8619 + ( ) × 0.142 × 0.8618 }
1 2
= 1 − {0.04897 + 0.15945 + 0.24659} = 𝟎. 𝟓𝟒𝟓
(ii) Now, success is getting no rotten apples from the 20 apples plucked. So, we should first find the
probability of no rotten apples from the 20 plucked from a tree, using 𝑋~𝐵(20, 0.14)
𝑝 = 𝑃(𝑋 = 0) = 0.8620 = 0.04897
Now, 𝑌~𝐵(10, 0.04897).
𝑃(𝑌 ≥ 3) = 1 − 𝑃(𝑌 ≤ 2)

17
 10 10
= 1 − {0.9510310 + ( ) × 0.04897 × 0.951039 + ( ) × 0.048972 × 0.951038 }
1 2
= 1 − {0.60526 + 0.31166 + 0.07221} = 𝟎. 𝟎𝟏𝟎𝟗
(iii) Now, success is getting at most 2 rotten apples from the 20 plucked. So, we should first find the
probability of at most 2 rotten apples from the 20 plucked from a tree, using 𝑋~𝐵 (20, 0.14)
𝑝 = 𝑃(𝑋 ≤ 2) = 0.04897 + 0.15945 + 0.24659 = 0.455
Now, 𝑌~𝐵(10, 0.455).
𝑃(𝑌 ≥ 8) = 𝑃(𝑌 = 8,9,10)
10 10
= 0.45510 + ( ) × 0.545 × 0.4559 + ( ) × 0.5452 × 0.4558
9 8
= 0.00038029 + 0.004555 + 0.02455 = 𝟎. 𝟎𝟐𝟗𝟓
Example II – 4: There are 𝟐𝟎% green boards and 𝟑𝟔% black boards in a stationary shop, and the
remaining are white boards. Simon bought 𝒏 boards. Find the least value of 𝒏 for which the probability
that Simon bought at least one green board is at least 𝟎. 𝟗𝟗.
Here, 𝑋~𝐵(𝑛, 0.2). It is given that,
𝑃(𝑋 ≥ 1) ≥ 0.99
1 − 𝑃(𝑋 = 0) ≥ 0.99
1 − 0.8𝑛 ≥ 0.99
−0.8𝑛 ≥ −0.01
0.8𝑛 ≤ 0.01
For solving this exponential inequality, we can use two methods.
Trial and error method:
Applying different values for 𝑛 and checking whether 0.8𝑛 is lesser than 0.01.
When 𝑛 = 10, 0.810 = 0.1074 > 0.01,
When 𝑛 = 15, 0.815 = 0.03518 > 0.01,
When 𝑛 = 20, 0.820 = 0.01153 > 0.01,
When 𝑛 = 21, 0.821 = 0.00922 < 0.01.
For all the values of 𝑛 ≥ 21, 0.8𝑛 < 0.01. The least value of 𝑛 is 𝟐𝟏 for which 𝑃(𝑋 ≥ 1) ≥ 0.99.
Logarithm method:
Taking logarithm on both sides,
ln 0.8𝑛 ≤ ln 0.01 (We can also use log instead of ln)
Applying the law ln 𝐴𝑝 = 𝑝 ln 𝐴,
𝑛 ln 0.8 ≤ ln 0.01
Both ln 0.8 and ln 0.01 are negative, so the inequality sign has changed.
ln 0.01
𝑛≥
ln 0.8
𝑛 ≥ 20.64
Hence, 𝒏 = 𝟐𝟏.

18
Example II – 5: A television channel conducts a reality show for two seasons. The following two-way
table shows the number of people who participated in each season.

𝐌𝐚𝐥𝐞 𝐅𝐞𝐦𝐚𝐥𝐞 𝐓𝐨𝐭𝐚𝐥

𝐒𝐞𝐚𝐬𝐨𝐧 𝟏 12 18 30

𝐒𝐞𝐚𝐬𝐨𝐧 𝟐 15 15 30

𝐓𝐨𝐭𝐚𝐥 27 33 60

𝟏𝟎 people are to be chosen from both seasons for a stage show.

(i) 𝟏𝟎 females are selected at random. Find the probability that at least two females are participants
of season 𝟐.
𝟒𝟎% of the males are good at dancing and the remaining are good at singing. Similarly, 𝟔𝟓% of the
females are good at dancing and remaining are good at singing.
(ii) 𝟏𝟎 singers are chosen at random. Find the probability that at least one is a male.
15 5
(i) Here, 𝑛 = 10, 𝑝 = = .
33 11

𝑃(𝑋 ≥ 2) = 1 − 𝑃(𝑋 = 0,1)

6 10 10 5 6 9
= 1 − {( ) + ( ) × ( ) × ( ) }
11 1 11 11
= 1 − {0.0023312 + 0.01943} = 𝟎. 𝟗𝟕𝟖
(ii) This is conditional probability. The condition is “selected a singer” and we are supposed to find the
probability of selecting a male.
27 33
𝑃(𝑆𝑖𝑛𝑔𝑒𝑟𝑠) = 𝑃(𝑆) = × 0.60 + × 0.35 = 0.4625
60 60
27
𝑃(𝑆𝑖𝑛𝑔𝑒𝑟 𝑎𝑛𝑑 𝑀𝑎𝑙𝑒) = 𝑃(𝑆 ∩ 𝑀) = × 0.60 = 0.27
60
𝑃(𝑆 ∩ 𝑀) 0.27
𝑃(𝑀⁄𝑆) = = = 0.58378
𝑃 (𝑆) 0.4625
Now, 𝑛 = 10, 𝑝 = 0.58378 and we are supposed to find 𝑃(𝑋 ≥ 1)
𝑃(𝑋 ≥ 1) = 1 − 𝑃(𝑋 = 0) = 1 − 0.416210 = 𝟎. 𝟗𝟗𝟗𝟖

Exercise II
1. Saanvi keeps the leftover fruits of each day in the fridge. The probability that she forgets to keep the
leftover fruits in the fridge on any day is 0.15. If she keeps the fruits in the fridge there is a probability
of 0.1 that the fruits will get rotten. If she does not keep the fruits in the fridge there is a probability of
0.85 that the fruits will get rotten.
(i) Find the probability that she forgets to keep the left fruits in the fridge on fewer than 3 of the next
10 days.
(ii) Find the probability that the fruits get rotten on any particular day.
(iii) Find the mean and variance of the number of times she forgets to keep the fruits in the fridge for
20 days.

19
2. Random packets of chocolates are said to have gift cards inside. The mean number of gift cards in 25
packets of chocolates is given by 5. Calculate the probability that randomly chosen 25 packets of
chocolates will have more than 5 gift cards inside.
3. Strawberries are sold in packets of 20. There is a constant probability that any strawberry is damaged,
independent of other strawberries. The mean number of damaged strawberries in a packet has been found
to be 4.8. Find the probability that a packet contains between 1 and 4 (inclusive) damaged strawberries.
4. A biased die was thrown 10 times and the number of 4’s was noted. This experiment was repeated many
times and the average number of 4’s was found to be 3.6. Find the probability that in the next 10 throws
the number of 4’s will be greater than 2.
5. A magician plays 30 tricks in a show. For each trick, the probability that it fails in a show is 0.045,
independent of other tricks.
(i) Find the probability that more than 1 trick fails in a show.
The materials needed for the tricks per show costs $15 per trick. 500 people pay $10 each to watch the
show. If more than 1 trick fails they get their money back.
(ii) Calculate the expected profit for the magician.
6. Vihan has 30 books, some of which are hard-bounded. He has novels, comics and cartoon books. The
following two-way table summarises the number of these books.

𝐏𝐚𝐩𝐞𝐫 − 𝐛𝐨𝐮𝐧𝐝𝐞𝐝 𝐇𝐚𝐫𝐝 − 𝐛𝐨𝐮𝐧𝐝𝐞𝐝 𝐓𝐨𝐭𝐚𝐥

𝐍𝐨𝐯𝐞𝐥𝐬 6 2 8

𝐂𝐨𝐦𝐢𝐜𝐬 8 4 12

𝐂𝐚𝐫𝐭𝐨𝐨𝐧𝐬 7 3 10

𝐓𝐨𝐭𝐚𝐥 21 9 30

Vihan chooses 1 book at random to read.

(i) Find the probability that he reads a hard-bounded comic book.
(ii) Find the probability that he reads a cartoon book.
(iii) Find the probability that he reads a novel, given that he reads a hard-bounded book.
(iv) State, with a reason, whether the events ‘Vihan reads a paper-bounded book’ and ‘Vihan reads a
cartoon book’ are independent.
Vihan reads a book at random each day.
(v) Find the probability that Vihan reads a hard-bounded book on at most 3 of the next 10 days.
7. Ashish has a deck of cards in which the numbers 1 to 9 inclusive are printed, one number per card. He
picks 6 cards randomly from the deck of cards.
(i) Find the probability that at least 4 of the 6 cards have numbers less than or equal to 5 printed on
them.
Ashish now picks 𝑛 cards from the deck. The random variable 𝑋 is the number of these 𝑛 cards which
have the numbers less than or equal to a certain integer 𝑏 between 1 and 9 inclusive printed on them. It
is given that the mean of 𝑋 is 126 and the variance of 𝑋 is 28.
(ii) Find the values of 𝑛 and 𝑏.

20
8. A company plans a family get-together and a small celebration for their employees. 45% of the
employees are males. 60% of the males are married and 80% of the females are married.
(i) 8 females are chosen for performing a classical dance. Find the probability that more than 2 of
them are unmarried.
(ii) 10 married people are chosen at random for a drama. Find the probability that at least 3 of them
are male.
9. Advik goes walking every day in the morning. While going walking, the probability of meeting his
friend Arnav on any day is 0.32.
(i) Find the probability that, in any given week, Advik meets his friend on more than 2 days.
(ii) For five randomly chosen weeks, find the probability that exactly two of these weeks will have at
least 1 day where he meets his friend Arnav.
10. The probability that Aryan catches his office bus on time on any day is 0.85.
(i) Aryan goes to his office on 𝑛 days. Find the least value of 𝑛 for which the probability that he
catches his office bus on all 𝑛 days on time is less than 0.01.
Aryan goes to his office on 20 days of every month. The number of days he catches his office bus on
time is denoted by 𝑋.
(ii) Find the value of 𝑋 that has the highest probability. You may assume that this value is one of the
two values closest to the mean of 𝑋.
(iii) Find the probability that in exactly 4 of the next 6 months Aryan catches his office bus on time
on more than 18 days.
11. A product is rated ‘poor’ in quality by 15% of customers, ‘good’ in quality by 55% of customers and
‘excellent’ by 30% of customers. The manufacturer selects a random sample of 20 customers who
bought the product.
(i) Find the probability that more than 3 and fewer than 17 of them rated the product as ‘good’.
Then, the manufacturer selects a random sample of 𝑛 customers who bought the product.
(ii) Find the smallest value of 𝑛 for which the probability that at least 1 person will rate the product
as ‘poor’ is greater than 0.96.
12. Ishaan uses his calculator to produce 25 random integers between 8 and 48 inclusive. The random
variable 𝑋 is the number of these 25 integers which are multiples of 8.
(i) State the distribution of 𝑋 and give its parameters.
(ii) Calculate the probability 𝑃(1 ≤ 𝑋 ≤ 3).
Ishaan now produces 𝑛 random integers between 8 and 48 inclusive.
(iii) Find the least possible value of 𝑛 if the probability that none of these integers is a multiple of 8 is
less than 0.01.
13. In a large box of crayons, 20% of crayons are red in colour, 50% of crayons are blue in colour and 30%
of crayons are green in colour.
(i) Rohan selects 15 crayons at random. Find the probability that fewer than 12 crayons are blue or
green in colour.
(ii) Rohan selects 𝑛 crayons at random. The probability that none of these 𝑛 crayons are red in colour
is at least 0.01. Find the largest possible value of 𝑛.

21
 Unit – III
Geometric Distribution
Geometric Distribution:
Geometric distribution is another example of discrete random variables.
Geometric distribution is used for events which might be repeated again and again until a success has occurred.
Few examples are:
1. Throwing a die repeatedly until getting a six as the outcome.
2. Tossing two coins repeatedly until getting two heads together.
For these events, the expected outcome is called ‘success’ and the other outcome is called ‘failure’.
For the first event, success is getting a 𝟔 and the failure is not getting a 6.
For the second event, success is getting two heads together and the failure is not getting two heads together.

Conditions for Geometric Distribution:

The conditions for geometric distribution are the same as binomial distribution, except the number of trials is
not fixed. It depends on the trial at which success occurs.
1. The number of trials (𝒏) is the trial at which the first success occurs.
For example:
a. Say, ‘getting a 6’ is success while throwing a die, and the first 6 occurred on the 𝟏𝟎th throw.
b. Say, ‘getting heads’ is success while tossing a coin, and the first heads occurred on the 𝟐𝟎th toss.
2. A single trial has exactly two possible outcomes (success and failure) and these are mutually
exclusive.
3. The outcome of each trial is independent of the outcome of all the other trials.
4. The probability of success at each trial is constant.

Definition of Geometric Distribution:

From the conditions, it is evident that geometric distribution is dependent on the probability of success (𝑝).
Hence, 𝑝 is the parameter of geometric distribution.
Therefore, geometric distribution is defined as

𝑿~𝑮𝒆𝒐(𝒑)
where 𝑿 is the random variable and 𝒑 is the probability of success.
Since the outcomes success and failure are mutually exclusive, their probabilities add up to 1.

𝒑+𝒒=𝟏
Probability Mass Function of Geometric Distribution:
1 5
Say, you roll a die and expect 6 as the output. Hence, 𝑝 = , 𝑞 = .
6 6
1
If you get 6 on the first attempt, then 𝑃(𝑋 = 1) = .
6
5 1
If you get 6 on the second attempt, that means the first attempt is a failure. Hence, 𝑃(𝑋 = 2) = × .
6 6

5 5 1 5 2 1
If you get 6 on the third attempt, then 𝑃(𝑋 = 3) = × × = ( ) × .
6 6 6 6 6

5 5 5 1 5 3 1
If you get 6 on the fourth attempt, then 𝑃(𝑋 = 4) = × × × = ( ) × .
6 6 6 6 6 6

22
Hence, we can generalise it as follows, if the probability of success is taken as 𝑝:
If we get success on the 𝑟th attempt, then
𝑷(𝑿 = 𝒓) = (𝟏 − 𝒑)𝒓−𝟏 𝒑 = 𝒒𝒓−𝟏 𝒑
The probability mass function of geometric distribution is given by:

𝑷(𝑿 = 𝒙) = (𝟏 − 𝒑)𝒙−𝟏 𝒑
where 𝑥 = 1, 2, …, 𝑛.
The probability mass function of geometric distribution also satisfies
𝒏

∑ 𝑷(𝑿 = 𝒙) = 𝟏
𝒙=𝟎

Representation of Probability Mass Function:

As for binomial and probability distribution, we can represent the probability mass function of geometric
distribution in the form of either a table, lines or bars.
Let’s see the variation of the probability mass function of geometric distribution with various 𝑝 values by
plotting the points (𝒙, 𝑷(𝑿 = 𝒙)) in a graph.

Using Probability Mass Function to find cumulative probabilities:

If success occurs only after 𝑥 attempts, then the first 𝑥 attempts are all failures. Hence,

23
 𝑷(𝑿 > 𝒙) = (𝟏 − 𝒑)𝒙
𝑷(𝑿 ≥ 𝒙) = (𝟏 − 𝒑)𝒙−𝟏
If success occurs before 𝑥 attempts, then the complement of this event is the 𝑥 − 1 attempts are all failures.
Hence,

𝑷(𝑿 < 𝒙) = 𝟏 − (𝟏 − 𝒑)𝒙−𝟏

𝑷(𝑿 ≤ 𝒙) = 𝟏 − (𝟏 − 𝒑)𝒙
Expectation of Geometric Distribution:
The expectation of geometric distribution is
𝟏
𝐄𝐱𝐩𝐞𝐜𝐭𝐚𝐭𝐢𝐨𝐧 𝒐𝒓 𝐌𝐞𝐚𝐧 = 𝑬(𝑿) =
𝒑
Example III – 1: A fair tetrahedral die is thrown continuously until a four is obtained. Find the
probability that the four has occurred
(i) at the third throw,
(ii) first time at the third throw,
(iii) before the third throw,
(iv) after the third throw.
1
(i) In this question, getting the four is the success. Hence, 𝑝 = .
4
𝟏
Therefore, the probability that the four occurs at the third throw is .
𝟒
(ii) The probability that the four occurred for the first time at the third throw is
1 2 1 𝟗
𝑃(𝑋 = 3) = (1 − ) × =
4 4 𝟔𝟒
(iii) The probability that the four occurred before the third throw is
𝟕
𝑃(𝑋 < 3) = 1 − (1 − 0.25)3−1 =
𝟏𝟔
(iv) The probability that the four occurred after the third throw is
𝟐𝟕
𝑃(𝑋 > 3) = (1 − 0.25)3 =
𝟔𝟒

Example III – 2: The discrete random variable 𝑿 has a geometric distribution with mean 𝟐. 𝟓. Find
(i) 𝑷(𝑿 ≥ 𝟒),
(ii) 𝑷(𝑿 ≤ 𝟓)
(iii) the least integer 𝒏 such that 𝑷(𝑿 ≤ 𝒏) > 𝟎. 𝟗𝟗𝟓.
Mean is given as 2.5. Then,
1
= 2.5 ⇒ 𝑝 = 0.4
𝑝

(i) 𝑃(𝑋 ≥ 4) = (1 − 0.4)4−1 = 𝟎. 𝟐𝟏𝟔

(ii) 𝑃(𝑋 ≤ 5) = 1 − (1 − 0.4)5 = 𝟎. 𝟗𝟐𝟐𝟐𝟒.

24
(iii) 𝑃(𝑋 ≤ 𝑛) > 0.995
1 − (1 − 0.4)𝑛 > 0.995
0.6𝑛 < 0.005
Using logarithms,
log 0.6𝑛 < log 0.005
𝑛 log 0.6 < log 0.005
log 0.005
𝑛> ⇒ 𝑛 > 10.37 ⇒ 𝑛 = 11.
log 0.6

Exercise III
1. A fair six-sided die is thrown. Find the probability that the first time a 1 is obtained is
(i) on the second throw (ii) on the fifth roll
(iii) before the fifth roll (iv) after the fifth roll.
2. A fair five-sided spinner has sectors labelled 1,2,3,4,5. The spinner is spun until a 5 is scored. The
number of spins required to score a 5 is denoted by 𝑋. Find
(i) 𝑃(𝑋 = 4) (ii) 𝑃(𝑋 ≥ 4) (iii) 𝑃(𝑋 < 4)
(iv) State the relation between the answers of part (ii) and part (iii).
3. A fair four-sided spinner has sectors labelled 1,2,3 and 4. It is spun repeatedly until it lands on 3.
(i) Find the probability that
(a) on the first five spins it does not land on 3.
(b) it lands on 3 before the sixth spin
(c) on the first six spins it does not land on 3.
(d) the first time it lands on 3 is the sixth spin.
(ii) Find which three of your answers to part (i) add up to 1 and explain why.
(iii) The probability that it lands on 3 before the 𝑁th spin is greater than 0.96. Find the least possible
value of 𝑁.
4. Two fair six-sided dice are rolled until a total of a prime number is obtained.
(i) What is the probability that on any roll of the dice a total of a prime number is obtained?
(ii) Find the expected number of rolls that are needed to obtain the first total of a prime number.
(iii) The probability that it takes at least 𝑛 rolls to obtain the first total of a prime number is at least
10%. Find the greatest possible value of 𝑛.
5. A supermarket offers a gift coupon every day by randomly selecting a person from their first 10
customers. The probability of getting a gift coupon on any day is independent of the probability of getting
a gift coupon on any other day.
Alisha goes to the supermarket on all the days of a week as one of the first 10 customers. Find the
probability that
(i) she does not get any gift coupons
(ii) she gets at least one gift coupon
(iii) the first gift coupon she gets is on the last day of the week

25
 (iv) she does not get any gift coupons on the first five days but gets it on her sixth and seventh days.
6. An urn contains 4 red balls and 6 green balls. Carina picks up a ball randomly from the urn and replaces
it again in the urn. She keeps repeating this until she picks up a red ball from the urn.
(i) Find the probability that Carina picks up a red ball on her fourth attempt.
(ii) Find the probability that Carina picks up a red ball for the first time on her fourth attempt.
(iii) Find the probability that Carina takes at least 4 attempts to pick up a red ball.
(iv) Find the mean of the number of attempts it takes for Carina to pick up a red ball.
(v) Carina repeats this process 𝑛 times. Find the smallest value of 𝑛 for which there is a chance of
50% or more that she will pick up a red ball at least once.
7. Fair tetrahedral dice with faces labelled 1,2,3,4 are rolled, one at a time, until a 2 is scored.
(i) Find the probability that the first 2 is rolled on the fourth attempt.
(ii) Find the probability that it takes at least five attempts to roll the first 2.
(iii) Given that a 2 is not rolled in the first five attempts, find the probability that a 2 is rolled within
the next two attempts.
(iv) Write down the mean number of attempts that it takes to roll a 2.
8. A coin is biased such that the probability of getting heads is 0.7. Ishita and Navya were playing a game.
Ishita tosses the coin until she gets tails, after which it is Navya’s turn.
(i) Find the probability that Ishita tosses the coin a total of six times.
(ii) Find the probability that Ishita tosses the coin at least six times.
(iii) Find the average number of times that Ishita tosses the coin.
(iii) Find the probability that the both Ishita and Navya toss the coin a total of five times.
9. Ishank goes walking every day. While going walking, the probability that he meets his friend is 0.2. On
ten consecutive days of walking,
(i) what is the probability that he does not meet his friend?
(ii) what is the probability that he meets his friend on the tenth day?
(iii) what is the expectation of the number of days on which he meets his friend?
(iv) what is the expectation of the number of days on which he does not meet his friend?
10. Rohan and Nishil are playing a game in which they are supposed to hit a target with an arrow. For each
1
attempt the probability that Rohan hits the target is and for each attempt the probability that Nishil hits
4
1
the target is . Find the probability that Rohan takes
3

(i) exactly 5 attempts for the first hit,

(ii) more than 8 attempts for the first hit.
In order to qualify for a competition, they should hit the target within at most six attempts. When they
hit the target, no further attempts are taken.
(iii) Find the probability that Rohan qualifies for the competition.
(iv) Find the probability that exactly one of Rohan or Nishil qualifies for the competition.

26
 Unit – IV
Normal Distribution
Normal Distribution:
As binomial distribution is related to discrete random variables, normal distribution is related to continuous
random variables.
If 𝑋 is a continuous random variable, then it can have any values within a given range. All measurable
quantities like height, weight, distance, etc. comes under continuous random variables.
For example, if 𝑋 is the random variable that denotes the heights of grade 11 students in centimetres, then 𝑋
can have any values from, say, 150 cm to 180 cm. Decimal values and fractions are also considered.
Normal distribution is also known as Gaussian distribution.

Definition of Normal Distribution:

The continuous random variable 𝑿 is said to be normally distributed, if the values of 𝑿 are spread
symmetrically about the mean.
Hence, the mean value of the normal distribution is the median and also the mode.
Mean is an important parameter of normal distribution.
Now, we should know by how much all the other values of the random variable 𝑋 are distributed symmetrically
about the mean. Hence, we need to know the standard deviation, which gives how much each value is getting
deviated from the mean.
Hence, the parameters of normal distribution are mean (𝝁) and variance (𝝈𝟐 ), where 𝜎 is the standard
deviation.
Therefore, normal distribution is defined as

𝑿~𝑵(𝝁, 𝝈𝟐 )
Probability Density Function of Normal Distribution:
As we have probability mass functions (𝑃(𝑋 = 𝑥 )) for discrete random variables, we have probability density
functions (𝑓(𝑥 )) for continuous random variables.
A continuous random variable 𝑿 is said to be normally distributed, if the probability density function
is
𝟏 𝟏 𝒙−𝝁 𝟐
− ( )
𝒇(𝒙) = 𝒆 𝟐 𝝈
𝝈√𝟐𝝅
where,
𝒙 takes the values of random variables and it ranges from −∞ < 𝒙 < ∞,
𝝁 is the mean value, which ranges from −∞ < 𝝁 < ∞ and
𝝈 is the standard deviation, which is always greater than zero (𝝈 > 𝟎).

27
Representation of Probability Density Function of Normal Distribution:
The following figure shows the graph of probability density function (𝑓(𝑥 )) of a continuous random variable
which is normally distributed with mean 𝜇 and variance 𝜎 2 .

Properties of Normal Distribution Curves:

1. The normal distribution curve is symmetrical about the mean.
2. The number of values of the random variable 𝑋 below the mean is equal to the number of values of the
random variable 𝑋 above the mean, so the median is also equal to the mean.
3. The mean, median and mode are all equal.
4. The curve does not touch the baseline.
5. The normal distribution curve is a unimodal, bell-shaped curve.
6. The total area under the curve is always equal to unity, which shows that total probability is always equal
to one.
7. The probability 𝑃(𝑎 < 𝑋 < 𝑏), where 𝑎 and 𝑏 are two values of the random variable 𝑋, is given by the
area under the curve from 𝑋 = 𝑎 to 𝑋 = 𝑏. It is found using integration as follows:
𝑏
𝑃(𝑎 < 𝑋 < 𝑏) = ∫ 𝑓(𝑥 ) 𝑑𝑥
𝑎

where 𝑓(𝑥 ) represents the probability density function of the random variable 𝑋.

28
Effect of Mean in Normal Distribution Curves:
The following figure shows various normal distribution curves with different means and the same standard
deviation.

Curves with the same standard deviation, independent of the mean, looks similar. The only difference is that
the curve is shifted horizontally.
The maximum heights of the curves are also same.

Effect of Standard Deviation in Normal Distribution Curves:

The following figure shows various normal distribution curves with different standard deviations and the same
mean.

29
The probability of the mean reduces when the spread of the data is increases. For high standard deviation
values, the maximum height is very less.

Standard Normal Distribution:

A continuous random variable 𝑋 is said to be distributed as standard normal if its mean is zero and its
standard deviation is one.
The random variable which is distributed as standard normal is represented as 𝒁. Hence, the definition of
standard normal distribution is given as:

𝒁~𝑵(𝟎, 𝟏)

Any random variable which is normally distributed(𝑋) with mean 𝜇 and standard deviation(𝜎) can be
converted into a random variable which is standard normally distributed (𝑍) with mean 0 and standard
deviation 1 by performing a transformation of the curve (Translation and scaling) algebraically as follows:
𝑿−𝝁
𝒁=
𝟐 𝝈
𝑿~𝑵(𝝁, 𝝈 ) ⇒ 𝒁~𝑵(𝟎, 𝟏)
The formula that enables us to change from the 𝑋 −scale to the 𝑍 −scale and vice versa is
𝑿−𝝁
𝒁=
𝝈
This process of converting 𝑋 to 𝑍 is called standardising.

Need of Standard Normal Distribution:

We know that the probability is given by the area under the curve.
We also know that the curve of standard normal distribution is always the same.
The area under the standard normal curve from −∞ to various 𝒁 = 𝒛 values are calculated and have been
tabulated in a table, which is given on page 67.
Since we can transform any normal distribution curve into the standard normal distribution curve by the
method of standardising, we can use the table values to find probabilities.
Hence, standard normal distribution is important in finding probabilities for any random variables which are
normally distributed.

30
Normal Distribution Table:
The normal distribution table is also known as the normal distribution function.
At the top of the table, a small introduction about the table is given as shown below:

It is given that 𝑍 has a normal distribution with mean 0 and variance 1, which means it is standard normal
distribution.
The graph shown above the table clearly shows that the table is filled with the area under the curve below 𝑍 =
𝑧 and it is denoted as Ф(𝑧), which is read as ‘table value of 𝑧’. Hence,
Ф(𝑧) = 𝑃(−∞ < 𝑍 ≤ 𝑧) = 𝑃(𝑍 ≤ 𝑧)
The first column of the table is filled with 𝑧 values for one decimal place.

If the calculated 𝑧 value is correct to 2 decimal places, then the second decimal place’s value has to be taken
from the middle column of the first row of the table.
If the calculated 𝑧 value is correct to 3 decimal places, then the third decimal place’s value has to be taken
from the right-most columns where it is mentioned as ADD in the first row of the table.

Hence, we can read the probabilities Ф(𝑧) = 𝑃(𝑍 ≤ 𝑧) for 𝑧 values with a maximum of three decimal places.

31
For example, 𝑃(𝑍 ≤ 0.246) can be found as follows:
First, look at the row of 𝑧 = 0.2 as shown below:

Now, the second decimal place’s (4) value has to be taken from the first row as shown below:

Hence, from the table, the value of 𝑃(𝑧 ≤ 0.24) = 0.5948.

Now, the third decimal place’s (6) value has to be taken from the right-most columns of the first row as shown
below:

The value from the table corresponding to the third decimal place (6) in the row of 𝑧 = 0.2 is 23 as shown
above. This value has to be added with 0.5948 as follows:
𝑃(𝑍 ≤ 0.246) = 0.5948 + 0.0023 = 0.5971

Rules for using the Normal Distribution Table:

Remember that Ф(𝑧) denotes the table value of 𝑧.
Rule I: 𝑷(𝒁 ≤ 𝒂), where 𝒂 is a positive constant.

𝑷(𝒁 ≤ 𝒂) = = Ф(𝒂)

32
Rule II: 𝑷(𝒁 ≥ 𝒂), where 𝒂 is a positive constant.

EQUALS

𝑷(𝒁 ≥ 𝒂) = = 𝟏 − Ф(𝒂)

MINUS

33
Rule III: 𝑷(𝒁 ≥ −𝒂), where 𝒂 is a positive constant.

EQUALS
𝑷(𝒁 ≥ −𝒂) = = Ф(𝒂)

(SYMMETRY PROPERTY)

34
Rule IV: 𝑷(𝒁 ≤ −𝒂), where 𝒂 is a positive constant.

EQUALS
𝑷(𝒁 ≤ −𝒂) = = 𝟏 − Ф(𝒂)

(SYMMETRY PROPERTY)

35
Rule V: 𝑷(𝒂 ≤ 𝒁 ≤ 𝒃), where 𝒂 and 𝒃 are positive constants.

EQUALS

= Ф(𝒃)
𝑷 (𝒂 ≤ 𝒁 ≤ 𝒃 ) =
− Ф(𝒂)

MINUS

36
Rule VI: 𝑷(−𝒂 ≤ 𝒁 ≤ −𝒃), where 𝒂 and 𝒃 are positive constants.

EQUALS
𝑷(−𝒂 ≤ 𝒁 = Ф(𝒂)
≤ −𝒃) = − Ф(𝒃)

(SYMMETRY PROPERTY)

37
Rule VII: 𝑷(−𝒂 ≤ 𝒁 ≤ 𝒃), where 𝒂 and 𝒃 are positive constants.

EQUALS

= Ф(𝒃)
− (𝟏
𝑷(−𝒂 ≤ 𝒁 ≤ 𝒃)
− Ф(𝒂))
=
= Ф(𝒂)
+ Ф(𝒃) − 𝟏

MINUS

38
Rule VIII: 𝑷(−𝒂 ≤ 𝒁 ≤ 𝒂), where 𝒂 is a positive constant.
This can be derived from Rule VII.
𝑷(−𝒂 ≤ 𝒁 ≤ 𝒂) = 𝟐Ф(𝒂) − 𝟏

Summary of Rules for using the Normal Distribution Table:

𝑃(𝑍 < 𝑎) = 𝑃(𝑍 > −𝑎) = Ф(𝑎)
𝑃(𝑍 < −𝑎) = 𝑃(𝑍 > 𝑎) = 1 − Ф(𝑎)
𝑃(𝑎 < 𝑍 < 𝑏) = Ф(𝑏) − Ф(𝑎)
𝑃(−𝑎 < 𝑍 < −𝑏) = Ф(𝑎) − Ф(𝑏)
𝑃(−𝑎 < 𝑍 < 𝑏) = Ф(𝑎) + Ф(𝑏) − 1
𝑃(−𝑎 < 𝑍 < 𝑎) = 2Ф(𝑎) − 1
Example IV – 1: Find the values of the following probabilities using the normal distribution table.
(i) 𝑷(𝒁 ≥ −𝟎. 𝟑𝟔𝟕) (ii) 𝑷(𝒁 < −𝟏. 𝟏𝟗𝟒) (iii) 𝑷(𝟏. 𝟐 < 𝒁 < 𝟏. 𝟒)
(iv) 𝑷(|𝒁| < 𝟏. 𝟓𝟓) (v) 𝑷(|𝒁| ≥ 𝟏. 𝟓𝟓) (vi) 𝑷(−𝟎. 𝟗𝟒𝟓 ≤ 𝒁 < 𝟏. 𝟒𝟓)
(i) 𝑃(𝑍 ≥ −0.367) = Ф(0.367) (RULE III)
𝑃(𝑍 ≥ −0.367) = 𝟎. 𝟔𝟒𝟑 (FROM THE TABLE)
(ii) 𝑃(𝑍 < −1.194) = 1 − Ф(1.194) (RULE IV)
𝑃(𝑍 < −1.194) = 1 − 0.884 = 𝟎. 𝟏𝟏𝟔
(iii) 𝑃(1.2 < 𝑍 < 1.4) = Ф(1.4) − Ф(1.2) (RULE V)
𝑃(1.2 < 𝑍 < 1.4) = 0.9192 − 0.8849 = 𝟎. 𝟎𝟑𝟒𝟑
(iv) 𝑃(|𝑍| < 1.55) = 𝑃(−1.55 < 𝑍 < 1.55) = 2Ф(1.55) − 1 (RULE VIII)
𝑃(|𝑍| < 1.55) = 2 × 0.9394 − 1 = 𝟎. 𝟖𝟕𝟗
(v) 𝑃(|𝑍| > 1.55) = 𝑃(𝑍 ≤ −1.55 𝑜𝑟 𝑍 > 1.55) = 1 − 𝑃(−1.55 < 𝑍 < 1.55) = 1 − 0.879 = 𝟎. 𝟏𝟐𝟏
(vi) 𝑃(−0.945 ≤ 𝑍 < 1.45) = Ф(0.945) + Ф(1.45) − 1 (RULE VIII)
𝑃(−0.945 ≤ 𝑍 < 1.45) = 0.8277 + 0.9265 − 1 = 𝟎. 𝟕𝟓𝟒

Exercise IV – 1
Find the values of the following probabilities using the normal distribution table.
1. 𝑃(𝑍 < 1.478) 2. 𝑃(𝑍 < −1.003) 3. 𝑃(𝑍 > 0.332)
4. 𝑃(𝑍 > −1.111) 5. 𝑃(0.236 < 𝑍 < 1.854) 6. 𝑃(0 < 𝑍 < 0.9)
7. 𝑃(−1.77 ≤ 𝑍 ≤ −0.026) 8. 𝑃(−1.123 < 𝑍 < 0) 9. 𝑃(|𝑍| ≤ 2)
10. 𝑃(|𝑍| ≥ 1.5) 11. 𝑃(−0.996 < 𝑍 ≤ 1.47)

39
Application of Normal Distribution to Find Probabilities:
To find the probability of any continuous random variable which is normally distributed, follow these steps:
Step 1: Read the problem carefully and note down the mean (𝜇 ) and standard deviation (𝜎) given in the
problem.
Step 2: Formulate the required probability using proper notation forms such as 𝑃(𝑋 > 𝑎) or 𝑃(𝑎 < 𝑋 < 𝑏)
and so on.
Step 3: Standardise the given normal random variable (𝑋) to the standard normal random variable (𝑍).
𝑋−𝜇
𝑍=
𝜎
Step 4: Use the normal distribution table to read the values of probabilities for the calculated 𝑧 value and
apply the appropriate rules to find the required probability.
Example IV – 2: The time taken for a particular viral fever to be eradicated a certain city is normally
distributed with mean 𝟕. 𝟑 days and standard deviation 𝟐. 𝟏𝟒 days. Find the probability that, in a
randomly chosen case from the city, the viral fever takes longer than 𝟖 days to eradicate.
Step 1: 𝜇 = 7.3, 𝜎 = 2.14
Step 2: To find: 𝑃(𝑋 > 8)
Step 3:
𝑋−𝜇 8 − 7.3
𝑃(𝑋 > 8) = (𝑍 > ) = 𝑃 (𝑍 > ) = 𝑃(𝑍 > 0.327)
𝜎 2.14
Step 4: Using the normal distribution table and applying the appropriate rule,
𝑃(𝑍 > 0.327) = 1 − Ф(0.327) = 1 − 0.6281 = 𝟎. 𝟑𝟕𝟐
Example IV – 3: The volume of fruit juice in bottles, in millilitres, is normally distributed with mean
𝟒𝟗𝟖 and standard deviation 𝟗. 𝟔. Calculate the probability that a randomly selected bottle contains
more than 𝟒𝟗𝟓 millilitres and less than 𝟓𝟎𝟎 litres of fruit juice.
Step 1: 𝜇 = 498, 𝜎 = 9.6
Step 2: To find: 𝑃(495 < 𝑋 < 500)
Step 3:
495 − 498 500 − 498
𝑃(495 < 𝑋 < 500) = 𝑃 ( <𝑍< ) = 𝑃(−0.313 < 𝑍 < 0.208)
9.6 9.6
Step 4: Using the normal distribution table and applying the appropriate rule,
𝑃(−0.313 < 𝑍 < 0.208) = Ф(0.313) + Ф(0.208) − 1 = 0.6228 + 0.5824 − 1 = 𝟎. 𝟐𝟎𝟓
Example IV – 4: It is given that 𝑿~𝑵(𝟐𝟓𝟎. 𝟏, 𝟏𝟐𝟓).
(i) Find the probability that two randomly chosen values of 𝑿 are both greater than 𝟐𝟓𝟓.
(ii) Find the probability that a randomly chosen value of 𝑿 deviates within 𝟏. 𝟗𝟔 standard deviations
of the mean.
(i) 𝜇 = 250.1, 𝜎 2 = 125.
255 − 250.1
𝑃(𝑋 > 255) = 𝑃 (𝑍 > ) = 𝑃(𝑍 > 0.438) = 1 − Ф(0.438)
√125
𝑃(𝑋 > 255) = 1 − 0.6693 = 0.3307
Two values of 𝑋 are taken. The probability that both values of 𝑋 are greater than 255 is
𝑃(> 255, > 255) = 0.3307 × 0.3307 = 𝟎. 𝟏𝟎𝟗

40
(ii) A deviation within 1.96 standard deviations of the mean can be on either side of the mean, that is,
between 𝜇 − 1.96𝜎 and 𝜇 + 1.96𝜎.
𝜇 − 1.96𝜎 − 𝜇 𝜇 + 1.96𝜎 − 𝜇
𝑃(𝜇 − 1.96𝜎 < 𝑋 < 𝜇 + 1.96𝜎) = 𝑃 ( <𝑍< )
𝜎 𝜎
= 𝑃(−1.96 < 𝑍 < 1.96) = 2Ф(1.96) − 1 = 2 × 0.975 − 1 = 𝟎. 𝟗𝟓
Note:
(i) Deviation from mean within 𝑏 standard deviations ⇒ 𝝁 − 𝒃𝝈 < 𝑿 < 𝝁 + 𝒃𝝈
(ii) Deviation above mean within 𝑏 standard deviations ⇒ 𝟎 < 𝑿 < 𝝁 + 𝒃𝝈
(iii) Deviation below mean within 𝑏 standard deviations ⇒ 𝝁 − 𝒃𝝈 < 𝑿 < 𝟎
(iv) Deviation from mean more than 𝑏 standard deviations⇒ 𝑿 < 𝝁 − 𝒃𝝈 𝐨𝐫 𝑿 > 𝝁 + 𝒃𝝈
(v) Deviation above mean more than 𝑏 standard deviations⇒ 𝑿 > 𝝁 + 𝒃𝝈
(vi) Deviation below mean more than 𝑏 standard deviations⇒ 𝑿 < 𝝁 − 𝒃𝝈

Exercise IV – 2
1. Name the distribution and suggest suitable numerical parameters which can be used to model the heights,
in metres, of 20-year-old male students.
2. It is given that 𝑋~𝑁(54.6, 6.96).
(i) Find the probability that a randomly chosen value of 𝑋 lies between 53 and 56.
(ii) Find the probability that a randomly chosen value of 𝑋 is more than 55.
(iii) Find the probability that two randomly chosen values of 𝑋 are both lesser than 55.
3. It is given that 𝑋~𝑁(1.6, 4.52 ).
(i) Find the probability that a randomly chosen value of 𝑋 is less than −1.
(ii) Find the probability that a randomly chosen value of 𝑋 deviates within one standard deviation of
the mean.
1
4. The random variable 𝑊 is normally distributed with a positive mean 𝜇 and standard deviation 𝜇. Find
4
the probability that a randomly chosen value of 𝑊 is positive.
5. In a city in Spain, the level of rainfall, in mm, during monsoon has the distribution 𝑁(650, 3502 ).
(i) Find the probability that a randomly chosen rainy day in this city has a rainfall level between 550
mm and 750 mm.
The level of rainfall, in mm, in another city in Spain, during monsoon has a normal distribution with
mean 𝜇 and standard deviation 2.5𝜇.
(ii) Find the proportion of rainy days on which the rainfall level is more than 1.5 standard deviations
from the mean.
(iii) 100 rainy days are chosen at random. Find how many of these rainy days would be expected to
have a rainfall level which is more than 2 standard deviations above the mean.
6. The lengths of leaves, in cm, of certain plants are normally distributed. The lengths of the leaves are
classified as follows:
𝑠𝑚𝑎𝑙𝑙 𝑠𝑖𝑧𝑒𝑑 − 𝑡ℎ𝑒 𝑙𝑒𝑎𝑠𝑡 25% 𝑜𝑓 𝑙𝑒𝑛𝑔𝑡ℎ𝑠
𝑏𝑖𝑔 𝑠𝑖𝑧𝑒𝑑 − 𝑡ℎ𝑒 𝑙𝑜𝑛𝑔𝑒𝑠𝑡 25% 𝑜𝑓 𝑙𝑒𝑎𝑣𝑒𝑠
𝑀𝑒𝑑𝑖𝑢𝑚 𝑠𝑖𝑧𝑒𝑑 − 𝑡ℎ𝑒 𝑟𝑒𝑚𝑎𝑖𝑛𝑖𝑛𝑔 50% 𝑜𝑓 𝑙𝑒𝑎𝑣𝑒𝑠

41
 Represent the above information in a normal distribution curve.
7. The random variable 𝑌 is normally distributed such that the mean 𝜇 is two times the standard deviation
𝜎. Find the probability that a randomly selected value of 𝑌 is more than 1.5 times the mean.
8. It is given that 𝑋~𝑁(150, 64), 𝑌~𝑁(150, 100), 𝑍~𝑁(250, 64) and 𝑊~𝑁(250, 100). On a single
diagram, with the horizontal axis going from 100 to 300, sketch four curves to represent the distributions
of 𝑋, 𝑌, 𝑍 and 𝑊.
9. The distance Bike 𝐴 can travel on 3 litres of fuel is normally distributed with mean 150 km and standard
deviation 15.6 km. The distance Bike 𝐵 can travel on 3 litres of fuel is normally distributed with mean
150 km and standard deviation 25.9 km. Both bikes are filled with 3 litres of fuel and driven to a place
175 km away.
(i) For each bike, find the probability that it runs out of fuel before it has travelled 175 km.
(ii) Using the result of part (i), conclude which bike is more efficient.
10. The random variable 𝑈 is normally distributed with mean 𝜇 and standard deviation 𝜎. Show that 80%
of the values of 𝑈 lie within 1.282 standard deviations of the mean.

Finding 𝒛 value from the given probability:

Say, 𝑃(𝑍 < 𝑎) = 0.6641. Let’s try to find the 𝑧 value corresponding to the probability 0.6641.
The value lesser than and closest to 0.6641 is found as 0.6628 in the table as shown below:

The next value 0.6664 is greater than 0.6641. Hence, 0.6628 is selected.
The corresponding 𝑧 value of 0.6628 is 𝟎. 𝟒𝟐 as shown below:

To get 0.6641, we need to add 0.0013 with 0.00628. However, the row which contains 0.6628 has 11 and
14 but not 13 as shown below:

However, 14 is closer to 13 than 11. Hence, we can take 14 and the corresponding table value 4 for including
it with the 𝑧 value 0.42. Hence, the actual 𝑧 value is 0.424.

42
After finding the value of 𝑧 from the table, the sign of 𝑧(+ or −) has to be determined.
Hence, we will now learn the rules to find the 𝑧 value from the probability value.
We use the notation Ф−𝟏 to represent the calculation of 𝑧 from the probability(𝑝).

Ф(𝒛) = 𝒑 ⇒ 𝒛 = Ф−𝟏 (𝒑)

Rule I: 𝑷(𝒁 < 𝒂) = 𝒑, where 𝒑 > 𝟎. 𝟓
The value of 𝑎 has to be positive so that 𝑃(𝑍 < 𝑎) > 0.5 as shown below:

𝑷(𝒁 < 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝒑)

43
Rule II: 𝑷(𝒁 < 𝒂) = 𝒑, where 𝒑 < 𝟎. 𝟓
The value of 𝑎 has to be negative so that 𝑃(𝑍 < 𝑎) < 0.5 as shown below:

The table has probability values starting from 0.5, so 𝑝 < 0.5 cannot be found in the table. Hence, we have to
find the 𝑧 value for 1 − 𝑝 as shown below:

𝑷(𝒁 < 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝟏 − 𝒑)

Rule III: 𝑷(𝒁 > 𝒂) = 𝒑, where 𝒑 > 𝟎. 𝟓

The value of 𝑎 has to be negative so that 𝑃(𝑍 > 𝑎) > 0.5 as shown below:

𝑷(𝒁 > 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝒑)

44
Rule IV: 𝑷(𝒁 > 𝒂) = 𝒑, where 𝒑 < 𝟎. 𝟓
The value of 𝑎 has to be positive so that 𝑃(𝑍 > 𝑎) < 0.5 as shown below:

𝑷(𝒁 > 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝟏 − 𝒑)

Rule V: 𝑷(−𝒂 < 𝒁 < 𝒂) = 𝒑
We know that,
𝑃(−𝑎 < 𝑍 < 𝑎) = 2Ф(𝑎) − 1
Hence,
𝑝+1
2Ф(𝑎) − 1 = 𝑝 ⇒ Ф(𝑎) =
2

−𝟏
𝒑+𝟏
𝒂=Ф ( )
𝟐
Summary of rules for finding the 𝒛 value from the probability:
𝑷(𝒁 < 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝒑)
𝑷(𝒁 < 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝟏 − 𝒑)
𝑷(𝒁 > 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝒑)
𝑷(𝒁 > 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝟏 − 𝒑)
𝒑+𝟏
𝑷(−𝒂 < 𝒁 < 𝒂) = 𝒑 ⇒ 𝒂 = Ф−𝟏 ( )
𝟐
Example IV – 5: Find the value of 𝒂 in each case:
(i) 𝑷(𝒁 < 𝒂) = 𝟎. 𝟑𝟒𝟐𝟔 (ii) 𝑷(𝒁 > 𝒂) = 𝟎. 𝟓𝟎𝟏 (iii) 𝑷(𝒁 < 𝒂) = 𝟎. 𝟗𝟔𝟗𝟔
(iv) 𝑷(𝒁 > 𝒂) = 𝟎. 𝟐𝟐𝟐 (v) 𝑷(−𝒂 < 𝒁 < 𝒂) = 𝟎. 𝟖
(i) 𝑃(𝑍 < 𝑎) = 0.3426 < 0.5 ⇒ 𝑎 = −Ф−1 (1 − 0.3426) = −Ф−1 (0.6574)
𝑎 = −𝟎. 𝟒𝟎𝟓 𝑜𝑟 − 𝟎. 𝟒𝟎𝟔
(ii) 𝑃(𝑍 > 𝑎) = 0.501 > 0.5 ⇒ 𝑎 = −Ф−1 (0.501)
𝑎 = −𝟎. 𝟎𝟎𝟐 𝑜𝑟 − 𝟎. 𝟎𝟎𝟑

45
(iii) 𝑃(𝑍 < 𝑎) = 0.9696 > 0.5 ⇒ 𝑎 = Ф−1 (0.9696)
𝑎 = 𝟏. 𝟖𝟕𝟒
(iv) 𝑃(𝑍 > 𝑎) = 0.222 < 0.5 ⇒ 𝑎 = Ф−1 (1 − 0.222) = Ф−1 (0.778)
𝑎 = 𝟎. 𝟕𝟔𝟓
(v) 𝑃(−𝑎 < 𝑍 < 𝑎) = 0.8
0.8 + 1
𝑎 = Ф−1 ( ) = Ф−1 (0.9) = 𝟏. 𝟐𝟖𝟐
2
Example IV – 6: In a city in Australia, the average temperature, in ℃, during winter is a random
variable with the distribution 𝑵(𝝁, 𝟖𝟎. 𝟏). In this city, the probability that a randomly chosen day in
the winter season has the average temperature above −𝟏℃ is 0.5883. Find the value of 𝝁.
Given that 𝑋~𝑁(𝜇, 80.1).
𝑃(𝑋 > −1) = 0.5883
−1 − 𝜇
𝑃 (𝑍 > ) = 0.5883
√80.1
−1 − 𝜇
= −Ф−1 (0.5883)
√80.1
−1 − 𝜇
= −0.223
√80.1
−1 − 𝜇 = −1.9958
𝝁 = 𝟎. 𝟗𝟗𝟔℃
Example IV – 7: It is given that 𝑿~𝑵(𝝁, 𝝈𝟐 ). The probability that a randomly selected value of 𝑿 is
lesser than 𝟒𝟕. 𝟏 is 𝟎. 𝟑𝟖𝟔. Also, the probability that a randomly selected value of 𝑿 is greater than 𝟓𝟒. 𝟖
is 𝟎. 𝟑𝟏𝟔. Find the values of 𝝁 and 𝝈.
Given that, 𝑃(𝑋 < 47.1) = 0.386.
47.1 − 𝜇
𝑃 (𝑍 < ) = 0.386
𝜎
47.1 − 𝜇
= −Ф−1 (1 − 0.386) = −Ф−1 (0.614)
𝜎
47.1 − 𝜇
= −0.289
𝜎
𝜇 = 47.1 + 0.289𝜎 − − − −(𝐴)
Given that, 𝑃(𝑋 > 54.8) = 0.684.
54.8 − 𝜇
𝑃 (𝑍 > ) = 0.316
𝜎
54.8 − 𝜇
= Ф−1 (1 − 0.316) = Ф−1 (0.684)
𝜎
54.8 − 𝜇
= 0.479
𝜎
𝜇 = 54.8 − 0.479𝜎 − − − −(𝐵)
Equating (𝐴) and (𝐵),
47.1 + 0.289𝜎 = 54.8 − 0.479𝜎

46
 0.768𝜎 = 7.7
𝜎 = 10.026 = 𝟏𝟎. 𝟎
Applying in (𝐴) ⇒
𝜇 = 47.1 + 0.289 × 10.026
𝜇 = 49.9975 = 𝟓𝟎. 𝟎
Example IV – 8: The weights of apples plucked from a particular garden have a normal distribution
with mean 𝟏𝟔𝟎 grams and standard deviation 𝟐𝟐 grams. The gardener split the apples into three
categories as follows:
𝒔𝒎𝒂𝒍𝒍 𝒂𝒑𝒑𝒍𝒆𝒔 − 𝒕𝒉𝒆 𝒍𝒆𝒂𝒔𝒕 𝟏𝟓% 𝒐𝒇 𝒘𝒆𝒊𝒈𝒉𝒕𝒔
𝒃𝒊𝒈 𝒂𝒑𝒑𝒍𝒆𝒔 − 𝒕𝒉𝒆 𝒉𝒆𝒂𝒗𝒊𝒆𝒔𝒕 𝟏𝟓% 𝒐𝒇 𝒘𝒆𝒊𝒈𝒉𝒕𝒔
𝑴𝒆𝒅𝒊𝒖𝒎 𝒂𝒑𝒑𝒍𝒆𝒔 − 𝒕𝒉𝒆 𝒓𝒆𝒎𝒂𝒊𝒏𝒊𝒏𝒈 𝟕𝟎% 𝒐𝒇 𝒘𝒆𝒊𝒈𝒉𝒕𝒔
Find the least and greatest weights of medium apples to 1 decimal place.
Let the weights of the apples are represented by a random variable 𝑋~𝑁(160,22).
The following graph shows the above given information.

The least weight for the medium apples is 𝐿 and the greatest weight for the medium apples is 𝐺 as shown in
the above figure.
From the graph, 𝑃(𝑋 < 𝐺 ) = 0.7 + 0.15 = 0.85
𝐺 − 160
𝑃 (𝑍 < ) = 0.85
22
𝐺 − 160
= Ф−1 (0.85) = 1.036
22
𝑮 = 𝟏𝟖𝟐. 𝟖 grams.
Because of the symmetrical nature of the curve,
𝐿 − 160
= −1.036
22
𝑳 = 𝟏𝟑𝟕. 𝟐 grams.

47
 Exercise IV – 3
1. The weights of biscuit packets, in grams, are normally distributed with mean 𝜇 and standard deviation
9.6. The weights were measured for 600 of these packets and it was found that 186 of them weighed
more than 420 grams.
(i) Calculate the value of 𝜇.
(ii) Five of these 600 packets are chosen at random. Calculate the probability that exactly 3 of them
weighs more than 420 grams.
2. The weights of wooden cases are normally distributed with mean 1.25 kg and standard deviation 𝜎 kg.
In a random sample of 200 such cases, 28 weighed less than 0.99 kg. Find the value of 𝜎.
3. The random variable 𝑋 is normally distributed with mean 𝜇 and standard deviation 𝜎. It is given that the
1
mean equals to 80% of the variance and that 𝑃 (𝑋 < 𝜇) = 0.333. Find the values of 𝜇 and 𝜎.
3

4. The random variable 𝑋 is the length of time, in minutes, that Rohan takes to finish his Mathematics
homework. 𝑋 has a normal distribution with mean 𝜇 and variance 𝜎 2 .
It is given that 𝑃(𝑋 > 60) = 0.215 and 𝑃(𝑋 < 20) = 0.147. Find 𝜇 and 𝜎.
5. The weights of a particular species of reptiles are modelled by a normal distribution. A researcher
measures the weights of a random sample of 500 reptiles of this species and finds that 88 weighs less
than 120 grams and 280 weighs more than 215 grams.
(i) Find estimates of the mean and standard deviation of the weights of reptiles of this species.
(ii) In a random sample of 400 reptiles of this species, how many would the researcher expect to find
with weights more than 1 standard deviation from the mean?
6. The diameter of spherical copper balls, 𝑋 cm, manufactured in a factory are normally distributed. 95%
of the diameters are less than 146 cm and 75% of the diameters are more than 96 cm.
(i) Find the mean and the standard deviation of the diameters of the spherical balls.
(ii) Find the value of 𝑎 such that 𝑃(90 < 𝑋 < 𝑎) = 0.5.
7. It is given that 𝑊~𝑁(250, 502 ). Find the value of 𝑏 given that 𝑃(250 − 𝑏 < 𝑊 < 250 + 𝑏) = 0.5.
8. The volume of oil in a can is normally distributed with mean 996 ml and standard deviation 10.5 ml. It
is found that 90% of the cans contain between (996 − 𝑐) ml and (996 + 𝑐) ml. Find the value of 𝑐.
9. The times taken by Saira to solve a mathematics problem has a normal distribution with mean 30 minutes
and standard deviation 16 minutes. Saira classifies the difficulty level of the mathematics problem
depending on the time she takes for solving as follows:
𝐸𝑎𝑠𝑦 − 𝑡ℎ𝑒 𝑠ℎ𝑜𝑟𝑡𝑒𝑠𝑡 35% 𝑜𝑓 𝑠𝑜𝑙𝑣𝑖𝑛𝑔 𝑡𝑖𝑚𝑒𝑠
𝐻𝑎𝑟𝑑 − 𝑡ℎ𝑒 𝑙𝑜𝑛𝑔𝑒𝑠𝑡 35% 𝑜𝑓 𝑠𝑜𝑙𝑣𝑖𝑛𝑔 𝑡𝑖𝑚𝑒𝑠
𝑀𝑒𝑑𝑖𝑢𝑚 − 𝑡ℎ𝑒 𝑟𝑒𝑚𝑎𝑖𝑛𝑖𝑛𝑔 30% 𝑜𝑓 𝑠𝑜𝑙𝑣𝑖𝑛𝑔 𝑡𝑖𝑚𝑒𝑠
Find the least and greatest solving times for the mathematics problems for which the difficulty level is
Medium.
10. Sheets made of plywood are classified by thickness as thin, medium and thick. The thickness can be
modelled by a normal distribution with mean 3.2 cm and standard deviation 0.99 cm. Sheets with a
thickness of more than 3.6 cm are classified as thick.
(i) Find the probability that a sheet chosen at random is classified as thick.
(ii) The rest of the sheets are classified as thin and medium in such a way that there are twice as many
thin sheets as there are medium ones. Find the thickness below which the sheets are classified as
thin.

48
11. Distances covered by a taxi per month were noted down over a period of one year. A box-and-whisker
plot of the data obtained is displayed below.

It is suggested that distances covered can be modelled approximately by a normal distribution with mean
𝜇 km and standard deviation 𝜎 km. Estimate the value of 𝜇 and 𝜎.

Binomial to Normal Approximation:

For a random variable 𝑋, which has the distribution 𝐵(𝑛, 𝑝), when 𝑛 becomes too large such that 𝑛𝑝 > 5 and
𝑛𝑞 > 5, the distribution becomes symmetrical about the mean.
The following figure shows the graph of the probability mass function of 𝑋~𝑁(30, 0.4).

The horizontal axis takes the values of random variables, while the vertical axis takes the values of
corresponding probabilities.
We know that mean is calculated as 𝑛𝑝 = 30 × 0.4 = 12 and the above graph shows symmetry about the
mean at 𝑋 = 12.
In the following figure, the points are connected to show the symmetry of the data about the mean line at 𝑋 =
12.

49
Hence, for large values of 𝑛 for which both 𝑛𝑝 and 𝑛𝑞 are greater than 5, binomial distribution can be
approximated to normal distribution, for which the mean and variance are equal to 𝑛𝑝 and 𝑛𝑝𝑞 respectively.
𝒏 𝐢𝐬 𝐭𝐨𝐨 𝐥𝐚𝐫𝐠𝐞,
𝒏𝒑>𝟓,𝒏𝒒>𝟓
𝑿~𝑩(𝒏, 𝒑) ⇒ 𝑿~𝑵(𝒏𝒑, 𝒏𝒑𝒒)
Since we are approximating binomial distribution, which involves discrete random variables, to normal
distribution, which involves continuous random variables, we need to do continuity correction while
calculating probabilities.

Continuity Correction:
The following figure shows the representation of probability mass function of Binomial distribution with
𝐵(30, 0.4) as bars for random variables 13 ≤ 𝑋 ≤ 16.

50
The value of the random variable is marked at the middle of the width of each bar. The values of each bar
ranges from 𝑅. 𝑉 − 0.5 to 𝑅. 𝑉 + 0.5, where 𝑅. 𝑉 is the random variable. For example, in the above figure, the
width of the bar of the random variable 14 ranges from 13.5 to 14.5.
Since the width of each bar equals to 1 and the height of each bar equals to the probability of the particular
random variable (𝑥 ), the area of each bar equals the probability of the particular random variable (𝑃(𝑋 = 𝑥 )).
Hence,
𝑷(𝑿 = 𝟏𝟒) = 𝐀𝐫𝐞𝐚 𝐨𝐟 𝐭𝐡𝐞 𝐛𝐚𝐫 𝐫𝐚𝐧𝐠𝐞𝐬 𝐟𝐫𝐨𝐦 𝟏𝟑. 𝟓 𝐭𝐨 𝟏𝟒. 𝟓

Since in normal distribution, we assume that the distribution has a continuous curve and not bars, we find the
area under the curve using integration within the limits 13.5 to 14.5. This can be read from the normal
distribution table.
Hence, to find 𝑷(𝑿 = 𝟏𝟒) for binomial distribution, we need to find 𝑷(𝟏𝟑. 𝟓 ≤ 𝑿 ≤ 𝟏𝟒. 𝟓) using normal
approximation.
Now, to find the probability 𝑃(𝑋 < 14), we have to start from 13 to all the other values less than 13, as shown
below.

51
Since we have to include the bar of 13 as well, we need to start from the upper bound of 13 which is 13.5.
Hence, to find 𝑷(𝑿 < 𝟏𝟒) for binomial distribution, we need to find 𝑷(𝑿 ≤ 𝟏𝟑. 𝟓) using normal
approximation.
Similarly, to find the probability 𝑃(𝑋 ≤ 14), we have to start from 14 and to all the other values less than 14,
as shown below.

Since we have to include the bar of 14 as well, we need to start from the upper bound of 14 which is 14.5.
Hence, to find 𝑷(𝑿 ≤ 𝟏𝟒) for binomial distribution, we need to find 𝑷(𝑿 ≤ 𝟏𝟒. 𝟓) using normal
approximation.

From the above two figures, we can conclude that,

1. To find 𝑷(𝑿 > 𝟏𝟒) for binomial distribution, we need to find 𝑷(𝑿 ≥ 𝟏𝟒. 𝟓) using normal
approximation.
2. To find 𝑷(𝑿 ≥ 𝟏𝟒) for binomial distribution, we need to find 𝑷(𝑿 ≥ 𝟏𝟑. 𝟓) using normal
approximation.

52
The following table summarises the process of doing continuity correction:

Binomial Distribution Normal Approximation

𝑿~𝑩(𝒏, 𝒑) 𝑿~𝑵(𝒏𝒑, 𝒏𝒑𝒒)
𝑃(𝑋 = 𝑟) 𝑃(𝑟 − 0.5 ≤ 𝑋 ≤ 𝑟 + 0.5)

𝑃(𝑋 < 𝑟) 𝑃(𝑋 ≤ 𝑟 − 0.5)

𝑃(𝑋 ≤ 𝑟) 𝑃(𝑋 ≤ 𝑟 + 0.5)

𝑃(𝑋 > 𝑟) 𝑃(𝑋 ≥ 𝑟 + 0.5)

𝑃(𝑋 ≥ 𝑟) 𝑃(𝑋 ≥ 𝑟 − 0.5)

Example IV – 9: On a production line making plastic bottles, the probability of any bottle being faulty
is 𝟎. 𝟎𝟓. A random sample of 𝟑𝟎𝟎 bottles is inspected. Use a suitable approximation to find the
probability that there are at least 𝟏𝟎 faulty bottles.
Given data: 𝑋~𝐵(300, 0.05).
𝑛𝑝 = 300 × 0.05 = 15
𝑛𝑞 = 300 × 0.95 = 285
𝑛 is too large such that 𝑛𝑝 = 15 > 5 and 𝑛𝑞 = 285 > 0. Hence, we can approximate it to normal distribution.
𝜇 = 𝑛𝑝 = 15; 𝜎 2 = 300 × 0.05 × 0.95 = 14.25
9.5 − 15
𝑃(𝑋 ≥ 10) = 𝑃 (𝑍 > ) = 𝑃(𝑍 > −1.457)
√14.25
= Ф(1.457) = 𝟎. 𝟗𝟐𝟖

Exercise IV – 4
1. A die is biased such that the probability of landing a 4 is 0.6 and the probabilities of landing a 1, 2, 3, 5
or 6 are all equal.
(i) The die is rolled four times. Find the probability that the result is a 2, followed by a 4, followed by
an even number, followed by an odd number.
(ii) Find the probability that, out of 15 rolls of this die, at most 13 throws result in a 4.
(iii) The die is rolled 100 times. Using an appropriate approximation, find the probability that a 4 is
obtained less than 62 times.
2. On a particular railway track, 25% of the trains are goods trains, 40% are express trains and the
remaining are local trains.
(i) A random sample of 10 trains is taken. Find the probability that more than 2 trains are express
trains.
(ii) A random sample of 90 vehicles is now taken. Using a suitable approximation, find the probability
that less than 20 trains are goods trains.

53
3. On Sundays, Zubin spends 20% of the time playing online games. Zubin’s friend plays the same online
game once a day at a randomly chosen time.
(i) Find the probability that on randomly chosen 10 Sundays, there are exactly 3 Sundays on which
Zubin is playing the online game when his friend is also playing.
(ii) Another 15 Sundays are chosen at random. State, with a reason, whether it is appropriate to use a
normal approximation to find the probability that there are more than 8 Sundays on which Zubin
is playing the online game when his friend is also playing.
(iii) Find the probability that Zubin is playing the online game when his friend is also playing on at
least 12 of 50 randomly chosen Sundays.
4. (i) State three conditions that must be satisfied for a situation to be modelled by a binomial
distribution.
On any day, there is a probability of 0.25 that Malar is late to work.
(ii) Eight days are chosen at random. Find the probability that Malar is late to work on more than 7
days or fewer than 1 day.
(iii) 80 days are chosen at random. Find the probability that Malar is late to work on more than 25 days
or fewer than 17 days.
5. The times spent by passengers waiting for a bus at a particular bus stop in a city are independent and
normally distributed with a mean of 9.1 minutes. 35% of passengers have waited more than 10 minutes
for a bus.
(i) Find the standard deviation of the times spent by passengers waiting for a bus.
(ii) Find the probability that the time spent waiting for a bus by a randomly chosen passenger deviates
from the mean by more than 1 minute.
(iii) Find the probability that, of 5 randomly chosen passengers, more than 1 have waited less than 10
minutes.
(iv) Find the probability that, of 55 randomly chosen passengers, more than 25 have waited less than
9.1 minutes.
6. In a town in India, 75% of the days in a year are rainy on average. Assume that the weather on any one
day is independent of the weather on other days.
(i) Use a normal approximation to find the probability of there being fewer than 20 rainy days in the
town in the month of May (31 days).
(ii) Give a reason why the use of a normal approximation is justified.
7. Assume that, for a randomly chosen person, their next birthday is equally likely to occur on any day of
the week, independently of any other person’s birthday. Find the probability that, out of 420 randomly
chosen people, at most 50 will have their next birthday on a Sunday.
8. In a certain country, one person in four has brown hair on average.
(i) For a random selection of 𝑛 people, the probability that none of them have brown hair is less than
0.001. Find the least possible value of 𝑛.
(ii) For a random selection of 150 people, find the probability that more than 40 have brown hair.
9. At a bus stop in the morning rush hour, each person is either a student with probability 0.24, an office
worker with probability 0.18, a day worker with probability 0.44 or none of these.
(i) 6 people at the bus stop in a morning rush hour are chosen at random. Find the probability that
between 2 and 4 inclusive are day workers.

54
 (ii) 250 people at the bus stop in a morning rush hour are chosen at random. Find the probability that
between 56 and 67 inclusive are students.
10. Human blood groups are identified by two parts. The first part is 𝐴, 𝐵, 𝐴𝐵 or 𝑂 and the second part (the
Rhesus part) is + or −. The following table shows the percentage of people with the particular blood
groups in a city.

𝑨 𝑩 𝑨𝑩 𝑶

+ 42% 12% 5% 29%

− 6% 1% 3% 2%

(i) A random sample of 8 people in the city who are Rhesus + is taken. Find the probability that more
than 6 are group 𝐴 +.
(ii) A random sample of 200 people in the city is taken. Find the probability that more than 60 are
group 𝑂 +.

Problems involving Binomial and Normal Distribution:

Example IV – 10: The lengths of pieces of wooden boxes are normally distributed with mean 𝟏𝟗. 𝟔 cm
and standard deviation 𝟎. 𝟎𝟗𝟗 cm.
(i) Find the probability that a wooden box chosen at random has a length greater than 𝟏𝟗. 𝟓 cm.
(ii) Find the probability that, in a random sample of 𝟓 wooden boxes, at least three have lengths less
than 𝟏𝟗. 𝟓 cm.
(i) Given that, 𝑋~𝑁(19.6,0.0992 ).
19.5 − 19.6
𝑃(𝑋 > 19.5) = 𝑃 (𝑍 > ) = 𝑃(𝑍 > −1.01)
0.099
= Ф(1.01) = 0.8438 = 𝟎. 𝟖𝟒𝟒
(ii) 𝑃(𝑋 < 19.5) = 1 − 𝑃(𝑋 > 19.5) = 1 − 0.8438 = 0.1562
Now, the given distribution is 𝐵(5,0.1562).
𝑃(𝑋 ≥ 3) = 𝑃(𝑋 = 4) + 𝑃(𝑋 = 5)
5
= ( ) × 0.15624 × 0.8438 + 0.15625 = 𝟎. 𝟎𝟎𝟐𝟔𝟎
4

Exercise IV – 5
1. The volume, in millilitres, of shampoo in sachets are normally distributed with mean 5.65 ml and
standard deviation 0.525 ml.
(i) Find the probability that a randomly chosen sachet of shampoo contains more than 5.5 ml.
(ii) Find the value of 𝑐 such that 𝑃(𝑐 < 𝑋 < 5.7) = 0.45.
(iii) Eight shampoo sachets are chosen at random. Find the probability that less than two of the sachets
each contain less than 5.5 ml.

55
2. The distances that children of a particular age can cover during long jump have a normal distribution.
On average, 6 children out of 10 can cover a distance of more than 2.83 metres and 2 children out of 5
can cover a distance of more than 4.1 metres.
(i) Find the mean and standard deviation of the distances the children can cover.
(ii) Find the probability that a randomly chosen child will not be able to jump over a distance of 3.5
metres.
(iii) Find the probability that, of 6 randomly chosen children, at least 4 will be able to jump a distance
of more than 4.1 metres.
3. The lengths, in centimetres, of crayons produced in a factory have a normal distribution with mean 𝜇
and variance 0.81. It is given that 12% of the crayons are shorter than 10 cm.
(i) Find the value of 𝜇.
(ii) Find the probability that, of 5 crayons chosen at random, fewer than 2 will have a length between
9.6 cm and 10.5 cm.
4. The weights of bars of soap are normally distributed with mean 200 g. It is found that the weights of
96% bars of soap are within 10 g of the mean.
(i) Find the standard deviation of the weights of the bars of soap.
(ii) Find the probability that a randomly chosen bar of soap weighs more than 205 g
(iii) Find the probability that at least 1 of a random sample of 5 bars of soap have weights which are
more than 10 g above the mean.
5. The travel time of a State Express bus between two destinations can be assumed to have a normal
distribution with mean 40.1 minutes and standard deviation 5.6 minutes. Four trips of a State Express
bus between the two destinations are chosen at random.
(i) Find the probability that the State Express bus takes longer than 42 minutes on exactly two of these
trips.
The travel time of a Private Express bus between the same two destinations can also be assumed to have
a normal distribution. The probability that the time taken by a Private Express bus is more than 35
minutes is 0.25.
(ii) Assuming that the times taken to travel between the two destinations by both the State Express and
the Private Express buses are independent of each other, find the probability that, when both buses
are travelling between the destinations, their travel times are less than 35 minutes.
6. In a particular online game, the players can either gain or lose the money they are investing in it. The
random variable 𝑋 is the amount gained in a day, in hundreds of dollars, in the game. 𝑋 is normally
distributed with mean 3.6 and standard deviation 2.5.
(i) Find the probability that, on a randomly chosen day, a player gained an amount between $4200
and $5100.
(ii) Find the probability that the player makes a loss on exactly two of the next 5 consecutive days.
7. The random variable 𝑋 is such that 𝑋~𝑁(122, 196).
(i) A value of 𝑋 is chosen at random and rounded to the nearest whole number. Find the probability
that this whole number is 125.
(ii) Four independent observations of 𝑋 are taken. Find the probability that at least two of them are
lesser than 120.
(iii) Find the value of 𝑏 such that 𝑃(𝑏 < 𝑋 < 120) = 0.25.

56
 Answers
Unit I – Probability Distribution
Exercise I – 1
1. (i)
70
𝒙 210 105 70 52.5 42 35 30 26.25 21
3
1 2 3 4 5 6 7 8 9 10
𝑷(𝑿 = 𝒙)
55 55 55 55 55 55 55 55 55 55

18
(ii) 21 (iii)
55
1
2. 𝑏=
21

𝒚 1 2 3 4 5

𝑷(𝒀 = 𝒚) 𝑏 2𝑏 3𝑏 4𝑏 5𝑏

3. (i)

𝒙 0 1 2 3 4 5 7

𝑷(𝑿 = 𝒙) 0.2 0.16 0.16 0.16 0.16 0.08 0.08

(ii) 0.064 (iii) (0.2)𝑛−1 × 0.32

4.

𝒙 0 1 2 3
1 3 1 1
𝑷(𝑿 = 𝒙)
30 10 2 6

5.

𝒙 3 4 5 6 7 8 9 10 11 12

1 3 6 10 12 12 10 6 3 1
𝑷(𝑿 = 𝒙)
64 64 64 64 64 64 64 64 64 64

6.

𝒙 0 1 2

3 20 10
𝑷(𝑿 = 𝒙)
13 39 39

57
7.

𝒙 1 2 3 4 5 6 7 8 9 10 11 12

1 7 1 1 5 11 1 5 1 1 1 1
𝑷(𝑿 = 𝒙)
12 72 9 8 36 72 12 72 18 24 36 72

8.

𝒙 12 13 14 15
7 21 7 1
𝑷(𝑿 = 𝒙)
44 44 22 22

2 1
9. (i) (ii)
9 3
(iii)

𝒙 0 1 2

1 8 2
𝑷(𝑿 = 𝒙)
3 15 15

1
10. (i) 0.075 (ii) (a) 0.12 (b) 0.3 11. 𝑝=
3
Exercise I – 2
1. (i)
𝒙 0 1 2 3 4

𝑷(𝑿 = 𝒙) 0.6 0.24 0.096 0.0384 0.0256

(ii) 𝐸 (𝑋) = 0.6496

2. (i)

𝒙 0 1 2 3
5 10 5 1
𝑷(𝑿 = 𝒙)
42 21 14 21

4 5
(ii) 𝐸 (𝑋) = ; 𝑉𝑎𝑟(𝑋) =
3 9
3. (i)
𝒙 0 3 5 6 8
5 5 3 3 9
𝑷(𝑿 = 𝒙)
16 16 16 40 80

(ii) 𝐸 (𝑋) = 3.225; 𝑉𝑎𝑟(𝑋) = 7.0 (iii) 0.4

7 5 5 5
4. (i) 𝐸 (𝑋) = ; 𝑉𝑎𝑟(𝑋) = (ii) (iii)
3 9 18 72

58
 7
5. (i) 𝐸 (𝑋) = ; 𝑆. 𝐷 = 0.943
3
6. (i) (ii) 1.84

𝒘 0 2 4

𝑷(𝑾 = 𝒘) 0.38 0.32 0.3

7. (i) 𝑝 = 0.15; 𝑞 = 0.25 (ii) 3.89 8. 𝑎 = 0.2; 𝑏 = 0.12

2
9. (i) 𝐸 (𝑋) = (ii) 0.5 (iii) 𝑐 = 1
3
10. 𝑎 = 0.2, 𝑏 = 0.3, 𝑐 = 0.4
Unit II – Binomial distribution
Exercise II
1. (i) 0.820 (ii) 0.2125 (iii) 𝐸 (𝑋) = 3; 𝑉𝑎𝑟(𝑋) = 2.55
2. 0.383 3. 0.452 4. 0.759
5. (i) 0.394 (ii) $2582.05
2 1 2
6. (i) (ii) (iii) (iv) Independent (v) 0.650
15 3 9
7. (i) 0.453 (ii) 𝑛 = 162; 𝑏 = 7 8. (i) 0.203 (ii) 0.799
9. (i) 0.399 (ii) 0.00264
10. (i) 29 (ii) 17 (iii) 0.00968
6
11. (i) 0.995 (ii) 20 12. (i) 𝑋~𝐵 (25, ) (ii) 0.473 (iii) 30
41

13. (i) 0.352 (ii) 20

Unit III – Geometric distribution
Exercise III
5 625 671 3125
1. (i) (ii) (iii) (iv)
36 7776 1296 7776
64 64 61
2. (i) (ii) (iii) (iv) Sums up to one.
625 125 125
243 781 729 243
3. (i) (a) (b) (c) (d)
1024 1024 4096 4096
(ii) (b), (c) and (d). They cover all the possible outcomes. (iii) 𝑁 = 13
5
4. (i) (ii) 2.4 (iii) 𝑛 = 5
12
5. (i) 0.349 (ii) 0.651 (iii) 0.0531 (iv) 0.00590
6. (i) 0.4 (ii) 0.0864 (iii) 0.216 (iv) 2.5 (v) 𝑛=4
27 81 7
7. (i) (ii) (iii) (iv) 4
256 256 16
1
8. (i) 0.0504 (ii) 0.168 (iii) 3 (iv) 0.123
3

9. (i) 0.107 (ii) 0.0268 (iii) 2 (iv) 8

59
 81 6561 3367
10. (i) (ii) (iii) (iv) 0.235
1024 65536 4096
Unit IV – Normal distribution
Exercise IV – 1
1. 0.930 2. 0.158 3. 0.37 4. 0.867
5. 0.375 6. 0.316 7. 0.451 8. 0.369
9. 0.954 10. 0.137 11. 0.770
Exercise IV – 2
1. Normal; 𝜇 = 65 − 75, 𝜎 2 = 90 − 120
2. (i) 0.430 (ii) 0.440 (iii) 0.314
3. (i) 0.282 (ii) 0.683 4. 0.599
5. (i) 0.225 (ii) 0.134 (iii) 2 days
6. 7. 0.159

8.

9. (i) For bike 𝐴: 𝑃(𝑋 < 175) = 0.946; For bike 𝐵: 𝑃(𝑋 < 175) = 0.833 (ii) Bike 𝐵
Exercise IV – 3
1. (i) 415 (ii) 0.142 2. 0.241 3. 𝜇 = 0.525; 𝜎 = 0.81
4. 𝜇 = 42.9; 𝜎 = 21.6 5. (i) 𝜇 = 233.0; 𝜎 = 122.0 (ii) 126/127
6. (i) 𝜇 = 111.0; 𝜎 = 21.6 (ii) 𝑎 = 120 7. 𝑏 = 33.7
8. 𝑐 = 17.3 9. Least = 36.2; Greatest = 23.8
10. (i) 0.343 (ii) 3.05 11. 𝜇 = 125; 𝜎 = 29.7

60
 Exercise IV – 4
1. (i) 0.00876 (ii) 0.995 (iii) 0.620 2. (i) 0.833 (ii) 0.233
3. (i) 0.201 (ii) 𝑛𝑝 < 5 (iii) 0.298
4. (i) Constant/given probability, independent trials, fixed/given number of trials, two outcomes
(ii) 0.100 (iii) 0.261
5. (i) 2.34 (ii) 0.669 (iii) 0.946 (iv) 0.705
6. (i) 0.06 (ii) 𝑛𝑝 & 𝑛𝑞 both greater than 5 7. 0.0926
8. (i) 𝑛 = 25 (ii) 0.286 9. (i) 0.761 (ii) 0.614
10. (i) 0.0263 (ii) 0.348
Exercise IV – 5
1. (i) 0.613 (ii) 4.94 (iii) 0.120
2. (i) 𝜇 = 3.465, 𝜎 = 2.51 (ii) 0.506 (iii) 0.1792
3. (i) 𝜇 = 11.1 (ii) 0.706 4. (i) 4.87 (ii) 0.152 (iii) 0.0961
5. (i) 0.324 (ii) 0.0453 6. (i) 0.131 (ii) 0.0444
7. (i) 0.0276 (ii) 0.402 (iii) 110.0

61
 Module Summary
Unit I – Probability Distribution
Representing the values of random variables of a particular event along with the probability of its occurrence
in the form of a table is known as probability distribution.
▶ Properties of Probability Mass Function:
The value of 𝑃(𝑋 = 𝑥 ) lies between 0 and 1, that is, 𝟎 ≤ 𝑷(𝑿 = 𝒙) ≤ 𝟏.
The sum of all the probabilities equals to 1, that is, ∑𝑷(𝑿 = 𝒙) = 𝟏.
Discrete random variables can be represented as a probability distribution table, as lines (where the height of
each vertical line represents the probability of the particular random variable) or as bars (where the area of
each bar is equal to the probability of that random variable).

▶ Expectation and Variance of Probability Distribution:

The mean value of the random variables of a probability distribution is known as the expectation of the
probability distribution. It is denoted as 𝑬(𝑿) or

𝑬(𝑿) 𝒐𝒓 𝝁 = ∑𝒙𝒑
Variance (square of standard deviation) of the data can be calculated as
𝟐 𝟐 𝟐
𝑽𝒂𝒓(𝑿) 𝒐𝒓 𝝈 = ∑𝒙 𝒑 − (𝑬(𝑿))

Unit II – Binomial Distribution

Binomial distribution is an example of discrete random variables. Binomial distribution is used for events
which only have two possible outcomes.
▶ Conditions for Binomial Distribution:
1. A fixed number (𝑛) of trials take place.
2. A single trial has exactly two possible outcomes (success and failure) and these are mutually exclusive.
3. The outcome of each trial is independent of the outcome of all the other trials.
4. The probability of success at each trial is constant.

▶ Definition of Binomial Distribution:

Binomial distribution is defined as

𝑿~𝑩(𝒏, 𝒑)
where 𝑿 is the random variable, 𝒏 is the number of trials and 𝒑 is the probability of success.
Since the events success and failure are mutually exclusive, their probabilities add up to 1.

𝒑+𝒒=𝟏

▶ Probability Mass Function of Binomial Distribution:

The probability mass function of binomial distribution is given by:
𝒏
𝑷(𝑿 = 𝒙) = ( ) 𝒑𝒙 (𝟏 − 𝒑)𝒏−𝒙
𝒙

62
where 𝑥 = 0, 1, 2, …, 𝑛.
The probability mass function of binomial distribution also satisfies
𝒏

∑ 𝑷(𝑿 = 𝒙) = 𝟏
𝒙=𝟎
As for probability distribution, we can represent the probability mass function of binomial distribution in the
form of either a table, lines or bars.

Unit III – Geometric Distribution

Geometric distribution is another example of discrete random variables.
Geometric distribution is used for events which might be repeated again and again until a success has occurred.
▶ Conditions for Geometric Distribution:
The conditions for geometric distribution are the same as binomial distribution, except the number of trials is
not fixed. It depends on the trial at which success occurs.
1. The number of trials (𝑛) is the trial at which the first success occurs.
2. A single trial has exactly two possible outcomes (success and failure) and these are mutually exclusive.
3. The outcome of each trial is independent of the outcome of all the other trials.
4. The probability of success at each trial is constant.

▶ Definition of Geometric Distribution:

Geometric distribution is defined as

𝑿~𝑮𝒆𝒐(𝒑)
where 𝑿 is the random variable and 𝒑 is the probability of success.
Since the outcomes success and failure are mutually exclusive, their probabilities add up to 1.

𝒑+𝒒=𝟏

▶ Probability Mass Function of Geometric Distribution:

The probability mass function of geometric distribution is given by:

𝑷(𝑿 = 𝒙) = (𝟏 − 𝒑)𝒙−𝟏 𝒑
where 𝑥 = 1, 2, …, 𝑛.
The probability mass function of geometric distribution also satisfies
𝒏

∑ 𝑷(𝑿 = 𝒙) = 𝟏
𝒙=𝟎
As for binomial and probability distribution, we can represent the probability mass function of geometric
distribution in the form of either a table, lines or bars.

63
▶ Using Probability Mass Function to find cumulative probabilities:
If success occurs only after 𝑥 attempts, then the first 𝑥 attempts are all failures. Hence,

𝑷(𝑿 > 𝒙) = (𝟏 − 𝒑)𝒙

𝑷(𝑿 ≥ 𝒙) = (𝟏 − 𝒑)𝒙−𝟏
If success occurs before 𝑥 attempts, then the complement of this event is the 𝑥 − 1 attempts are all failures.
Hence,

𝑷(𝑿 < 𝒙) = 𝟏 − (𝟏 − 𝒑)𝒙−𝟏

𝑷(𝑿 ≤ 𝒙) = 𝟏 − (𝟏 − 𝒑)𝒙

▶ Expectation of Geometric Distribution:

The expectation of geometric distribution is
𝟏
𝐄𝐱𝐩𝐞𝐜𝐭𝐚𝐭𝐢𝐨𝐧 𝒐𝒓 𝐌𝐞𝐚𝐧 = 𝑬(𝑿) =
𝒑

Unit IV – Normal Distribution

As binomial distribution is related to discrete random variables, normal distribution is related to continuous
random variables.
▶ Definition of Normal Distribution:
The parameters of normal distribution are mean (𝝁) and variance (𝝈𝟐 ), where 𝜎 is the standard deviation.
Normal distribution is defined as

𝑿~𝑵(𝝁, 𝝈𝟐 )

▶ Probability Density Function of Normal Distribution:

As we have probability mass functions (𝑃(𝑋 = 𝑥 )) for discrete random variables, we have probability density
functions (𝑓(𝑥 )) for continuous random variables.
A continuous random variable 𝑋 is said to be normally distributed, if the probability density function is

𝟏 𝟏 𝒙−𝝁 𝟐
− ( )
𝒇(𝒙) = 𝒆 𝟐 𝝈
𝝈√𝟐𝝅
where,
𝒙 takes the values of random variables and it ranges from −∞ < 𝒙 < ∞,
𝝁 is the mean value, which ranges from −∞ < 𝝁 < ∞ and
𝝈 is the standard deviation, which is always greater than zero (𝝈 > 𝟎).

▶ Properties of Normal Distribution Curves:

1. The normal distribution curve is symmetrical about the mean.
2. The number of values of the random variable 𝑋 below the mean is equal to the number of values of the
random variable 𝑋 above the mean, so the median is also equal to the mean.
3. The mean, median and mode are all equal.

64
4. The curve does not touch the baseline.
5. The normal distribution curve is a unimodal, bell-shaped curve.
6. The total area under the curve is always equal to unity, which shows that total probability is always equal
to one.
7. The probability 𝑃(𝑎 < 𝑋 < 𝑏), where 𝑎 and 𝑏 are two values of the random variable 𝑋, is given by the
area under the curve from 𝑋 = 𝑎 to 𝑋 = 𝑏. It is found using integration as follows:
𝑏
𝑃(𝑎 < 𝑋 < 𝑏) = ∫ 𝑓(𝑥 ) 𝑑𝑥
𝑎

where 𝑓(𝑥 ) represents the probability density function of the random variable 𝑋.
▶ Standard Normal Distribution:
The definition of standard normal distribution is given as:

𝒁~𝑵(𝟎, 𝟏)
The formula that enables us to change from the 𝑋 −scale to the 𝑍 −scale and vice versa is
𝑿−𝝁
𝒁=
𝝈
This process of converting 𝑋 to 𝑍 is called standardising.

▶ Rules for using the Normal Distribution Table:

𝑃(𝑍 < 𝑎) = 𝑃(𝑍 > −𝑎) = Ф(𝑎)
𝑃(𝑍 < −𝑎) = 𝑃(𝑍 > 𝑎) = 1 − Ф(𝑎)
𝑃(𝑎 < 𝑍 < 𝑏) = Ф(𝑏) − Ф(𝑎)
𝑃(−𝑎 < 𝑍 < −𝑏) = Ф(𝑎) − Ф(𝑏)
𝑃(−𝑎 < 𝑍 < 𝑏) = Ф(𝑎) + Ф(𝑏) − 1
𝑃(−𝑎 < 𝑍 < 𝑎) = 2Ф(𝑎) − 1

▶ Application of Normal Distribution to Find Probabilities:

To find the probability of any continuous random variable which is normally distributed, follow these steps:
Step 1: Read the problem carefully and note down the mean (𝜇 ) and standard deviation (𝜎) given in the
problem.
Step 2: Formulate the required probability using proper notation forms such as 𝑃(𝑋 > 𝑎) or 𝑃(𝑎 < 𝑋 < 𝑏)
and so on.
Step 3: Standardise the given normal random variable (𝑋) to the standard normal random variable (𝑍).
𝑋−𝜇
𝑍=
𝜎
Step 4: Use the normal distribution table to read the values of probabilities for the calculated 𝑧 value and
apply the appropriate rules to find the required probability.

65
▶ Rules for finding the 𝒛 value from the probability:
𝑷(𝒁 < 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝒑)
𝑷(𝒁 < 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝟏 − 𝒑)
𝑷(𝒁 > 𝒂) = 𝒑 > 𝟎. 𝟓 ⇒ 𝒂 = −Ф−𝟏 (𝒑)
𝑷(𝒁 > 𝒂) = 𝒑 < 𝟎. 𝟓 ⇒ 𝒂 = Ф−𝟏 (𝟏 − 𝒑)
𝒑+𝟏
𝑷(−𝒂 < 𝒁 < 𝒂) = 𝒑 ⇒ 𝒂 = Ф−𝟏 ( )
𝟐

▶ Binomial to Normal Approximation:

For large values of 𝑛 for which both 𝑛𝑝 and 𝑛𝑞 are greater than 5, binomial distribution can be approximated
to normal distribution, for which the mean and variance are equal to 𝑛𝑝 and 𝑛𝑝𝑞 respectively.
𝒏 𝐢𝐬 𝐭𝐨𝐨 𝐥𝐚𝐫𝐠𝐞,
𝒏𝒑>𝟓,𝒏𝒒>𝟓
𝑿~𝑩(𝒏, 𝒑) ⇒ 𝑿~𝑵(𝒏𝒑, 𝒏𝒑𝒒)

▶ Continuity Correction:
The following table summarises the process of doing continuity correction:

Binomial Distribution Normal Approximation

𝑿~𝑩(𝒏, 𝒑) 𝑿~𝑵(𝒏𝒑, 𝒏𝒑𝒒)
𝑃(𝑋 = 𝑟) 𝑃(𝑟 − 0.5 ≤ 𝑋 ≤ 𝑟 + 0.5)

𝑃(𝑋 < 𝑟) 𝑃(𝑋 ≤ 𝑟 − 0.5)

𝑃(𝑋 ≤ 𝑟) 𝑃(𝑋 ≤ 𝑟 + 0.5)

𝑃(𝑋 > 𝑟) 𝑃(𝑋 ≥ 𝑟 + 0.5)

𝑃(𝑋 ≥ 𝑟) 𝑃(𝑋 ≥ 𝑟 − 0.5)

66
67
68
69