P and S - Unit 2

Download as pdf or txt
Download as pdf or txt
You are on page 1of 44

UNIT – 12

ONE DIMENSIONAL RANDOM VARIABLE


Topics in unit - I2
Discrete case
1. One dimensional random variable
Continuous case
2. Probability mass function
3. Probability density function
4. Moments
5. Moment generating function and their properties

RANDOM VARIABLE
Random Variable
A random variable is a rule that assign a numerical value to each possible outcome of an
experiment.
Example 1
In the experiment of throwing a coin twice the sample space S is S = { HH,HT,TH,TT}.
Let X be a random variable chosen such that X(S) = x ( the number of heads).

S = { HH,HT,TH,TT} -2 -1 0 1 2

Example 2
Let S be the sample space consisting of the numbers on a die. The sample space is S ={
1,2,3,4,5,6}. We define a RV by the function X(S)=2S (twice the number of points on a die).
The point in S now map onto the real line as the set {2,4,6,8,10,12 }

S = { 1, 2, 3, 4, 5, 6} 2 4 6 8 10 12
Random Variable (RV)

Real random variable (−∞. ∞) Complex random variable(𝒙 ± 𝒊𝒚)

Discrete RV Continuous RV Mixed RV

One dimensional RV Multi dimension RV

Probability mass function

Let 𝑋 be a discrete random variable which takes the values 𝑥1 , 𝑥2 , 𝑥3 , … …. such that

𝑃(𝑥𝑖 ) = 𝑃(𝑋 = 𝑥𝑖 ) ; 𝑖 = 1,2,3, …

then 𝑃(𝑥𝑖 ) is called the probability mass function (𝑝𝑚𝑓) of random variable 𝑋 and it satisfies
the following conditions

(𝑖) 𝑃(𝑥𝑖 ) ≥ 0 ; ∀ 𝑖 = 1,2,3, … .. (𝑖𝑖) ∑∞


𝑖=1 𝑃(𝑥𝑖 ) = 1.

Types of Random Variables

There are two types of random variables

(i) Discrete random variable (ii) Continuous random variable.

Discrete random variable

A random variable which can assume only a countable number of real values is
called a discrete random variable.

Example

1. The marks obtained by a student in an examination. Its possible values are 0,40,58, or 100.

2. Number of printing mistakes in each page of a book.

3. Number of telephone calls received by the telephone operator.


Probability distribution

The set {𝑥𝑖 , 𝑝𝑖 } is called the probability distribution of a random variable 𝑋 . The
probability distribution {𝑥𝑖 , 𝑝𝑖 } can be displayed in the form of table as show below.

𝑥𝑖 𝑥1 𝑥2 𝑥3 ………………
𝑝𝑖 𝑝1 𝑝2 𝑝3 ……………….

The distribution function of a random variable 𝑋 defined in (−∞, ∞) is given by 𝐹(𝑥) =


𝑃(𝑋 ≤ 𝑥) = ∑𝑖 𝑝𝑖 .

Example

Let S = {HH,HT,TH,TT}. Consider the random variable 𝑋 defined 𝑋 on S by X(S)=


x(number of heads) then 𝑋 is a discrete random variable because it can take only three values.
That is x=0, x=1, x=2.

1
𝑃1 = 𝑃(𝑋 = 0) = 𝑃(𝑇𝑇) = 4.

2 1
𝑃2 = 𝑃(𝑋 = 1) = 𝑃(𝐻𝑇, 𝑇𝐻) = = .
4 2

1
𝑃3 = 𝑃(𝑋 = 2) = 𝑃(𝐻𝐻) = 4.

Therefore the probability distribution is given by

1 1 1
{(𝑥1 , 𝑝1 ), (𝑥2 , 𝑝2 ), (𝑥3 , 𝑝3 )} = {(0, ) , (1, ) , (2, )}
4 2 4

(or)

𝑥𝑖 0 1 2
1 1 1
𝑝𝑖
4 2 4

Continuous random variable

A random variable 𝑋 which takes all possible values in a given interval is called
continuous random variable.
Example

Age, height, weight are continuous random variables.

Probability density function(p.d.f)

if 𝑋 is a continuous random variable such that


1 1
𝑃 {𝑥 − 2 𝑑𝑥 ≤ 𝑋 ≤ 𝑥 + 2 𝑑𝑥} = 𝑓(𝑥)𝑑𝑥. Then 𝑓(𝑥) is called the p.d.f of 𝑋, Provided

𝑓(𝑥) satisfies the following conditions (𝑖) 𝑓(𝑥) ≥ 0 (𝑖𝑖) ∫−∞ 𝑓(𝑥) = 1.

𝑏
Moreover , 𝑃(𝑎 ≤ 𝑋 ≤ 𝑏) 𝑜𝑟 𝑃(𝑎 < 𝑋 < 𝑏) is defined as 𝑃(𝑎 ≤ 𝑋 ≤ 𝑏) = ∫𝑎 𝑓(𝑥) 𝑑𝑥 .

Cumulative distribution function(cdf)


𝑥
𝐹(𝑥) = 𝑃[−∞ < 𝑋 ≤ 𝑥] = ∫−∞ 𝑓(𝑥)𝑑𝑥.

Properties of cdf

1. If 𝐹(𝑥) is a non decreasing function of 𝑋 . That is if 𝑥1 < 𝑥2 then 𝐹[𝑥1 ] ≤ 𝐹[𝑥2 ].

2. 𝐹[−∞] = 0 and 𝐹[∞] = 1.

3. If 𝑋 is discrete random variable taking values 𝑥1 , 𝑥2 , … … … where 𝑥1 < 𝑥2 … … . . <


𝑥𝑖−1 < 𝑥𝑖 < ⋯ … then 𝑃(𝑋 = 𝑥𝑖 ) = 𝐹[𝑥𝑖 ] − 𝐹[𝑥𝑖−1 ].

𝑑
4. If 𝑋 is a continuous random variable, then 𝐹[𝑥] = 𝑓(𝑥) at all points where 𝐹[𝑥]
𝑑𝑥
is differentiable.

Expectation (or) Mean

The averaging process, when applied to a random variable is called expectation. It is


denoted by 𝐸(𝑋) (or) 𝑋̅ and is read as the expected value of 𝑋 or the mean value of .

Case (i) For discrete random variable

Expectation 𝐸(𝑋) of the discrete random variable is given by 𝐸[𝑋] = ∑𝑖 𝑥𝑖 𝑝(𝑥𝑖 ) provided the
series is convergent.

Case (ii) For continuous random variable



if 𝑋 is a continuous random variable , then 𝐸[𝑋] = ∫−∞ 𝑥𝑓𝑋 (𝑥)𝑑𝑥 , Provided


∫−∞|𝑥|𝑓𝑋 (𝑥)𝑑𝑥 < ∞ , where 𝑓𝑋 (𝑥) is the p.d.f of the continuous random variable 𝑋.
Variance

Variance of 𝑋 = 𝐸[𝑋 2 ] − (𝐸[𝑋])2 . The variance of 𝑋 is denoted by (𝑋) 𝑜𝑟 𝜎 2 . The standard


deviation of 𝑋 is √𝜎 2 .

For discrete case: 𝐸[𝑋 2 ] = ∑𝑖 𝑥𝑖2 𝑝(𝑥𝑖 )



For continuous case: 𝐸[𝑋 2 ] = ∫−∞ 𝑥 2 𝑓𝑋 (𝑥)𝑑𝑥

Properties

1. The expectation of any given linear function of 𝑋 is equal to the sum of the linear
functions of the expectation of 𝑋,
𝐸[𝑎𝑋 + 𝑏] = 𝑎𝐸[𝑋] + 𝑏
2. The mathematical expectation of the sum of the random variables is equal to the sum of
the expectations, provided all the expectation exist.
𝐸[𝑋1 + 𝑋2 … … . +𝑋𝑛 ] = 𝐸[𝑋1 ] + 𝐸[𝑋2 ] + ⋯ . . 𝐸[𝑋𝑛 ]
3. The mathematical expectation of the product of a number of independent random
variables is equal to the product of their individual expectation.

𝐸[𝑋1 𝑋2 … … . 𝑋𝑛 ] = 𝐸[𝑋1 ]𝐸[𝑋2 ] … . . 𝐸[𝑋𝑛 ]

4. 𝑉𝑎𝑟(𝑋) ≥ 0.
5. 𝑉𝑎𝑟(𝑎) = 0. 𝑤ℎ𝑒𝑟𝑒 𝑎 𝑖𝑠 𝑎𝑛𝑦 𝑐𝑜𝑛𝑠𝑡𝑎𝑛𝑡.
6. 𝑉(𝑎𝑋) = 𝑎2 𝑉𝑎𝑟(𝑋). 𝑤ℎ𝑒𝑟𝑒 𝑎 𝑖𝑠 𝑐𝑜𝑛𝑠𝑡𝑎𝑛𝑡.

Moments

Let 𝑋 be a discrete random variable taking the values 𝑥1 , 𝑥2 , … … … 𝑥𝑛 𝑤th probability


mass function 𝑃1 , 𝑃2 , … … … 𝑃𝑛 respectively then the 𝑟 𝑡ℎ moment about the origin is
𝑛

𝜇𝑟 ′ (𝑎𝑏𝑜𝑢𝑡
𝑡ℎ𝑒 𝑜𝑟𝑖𝑔𝑖𝑛 ) = ∑ 𝑥𝑖𝑟 𝑝𝑖 (1)
𝑖=1

and
𝑛

𝜇𝑟 ′ (𝑎𝑏𝑜𝑢𝑡 𝑎𝑛𝑦 𝑝𝑜𝑖𝑛𝑡 𝑥 = 𝐴) = ∑(𝑥𝑖 − 𝐴)𝑟 𝑝𝑖 (2)


𝑖=1

and
𝑛

𝜇𝑟(𝑎𝑏𝑜𝑢𝑡 𝑚𝑒𝑎𝑛) = ∑(𝑥𝑖 − 𝑀𝑒𝑎𝑛)𝑟 𝑝𝑖 (3)


𝑖=1
In particular from (1)

𝜇1′ = ∑ 𝑥𝑖 𝑝𝑖 = 𝑀𝑒𝑎𝑛 (𝑋̅)


𝑖=1

𝜇2′ = ∑𝑛𝑖=1 𝑥𝑖2 𝑝𝑖 = 𝑀𝑒𝑎𝑛 𝑠𝑞𝑢𝑎𝑟𝑒 𝑣𝑎𝑙𝑢𝑒

𝜇2 = ∑𝑛𝑖=1(𝑥𝑖 − 𝑚𝑒𝑎𝑛)2 𝑝𝑖′ = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒

= 𝜇2′ − (𝜇1′ )2 [∵ 𝑋̅ = 𝜇1′ ]


3
𝜇3 = 𝜇3′ − 3𝜇2, 𝜇1′ + 2𝜇1′
2 4
𝜇4 = 𝜇4′ − 4𝜇3, 𝜇1′ + 6𝜇2′ 𝜇1′ − 3𝜇1′

Moments (Continuous case)

If 𝑋 is a continuous random variable with probability density function


𝑓(𝑥) then defined in the interval (𝑎, 𝑏)
𝑏

𝜇𝑟′ = ∫ 𝑥 𝑟 𝑓(𝑥)𝑑𝑥
𝑎

𝜇𝑟′ (𝑎𝑏𝑜𝑢𝑡 𝑎 𝑝𝑜𝑖𝑛𝑡 𝐴) = ∫(𝑥 − 𝐴)𝑟 𝑓(𝑥)𝑑𝑥


𝑎

𝜇𝑟(𝑎𝑏𝑜𝑢𝑡 𝑡ℎ𝑒 𝑚𝑒𝑎𝑛) = ∫(𝑥 − 𝑥̅ )𝑟 𝑓(𝑥)𝑑𝑥


𝑎

Moment Generating Function [M.G.F]

An important device that can be used to calculate the higher moments is the moment
generating function.

Moment generating function of a random variable 𝑋 about the origin is defined as

∑ 𝑒 𝑡𝑥 𝑝(𝑥) 𝑖𝑓 𝑋 𝑖𝑠 𝑑𝑖𝑠𝑐𝑟𝑒𝑡𝑒
𝑥
𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = ∞

∫ 𝑒 𝑡𝑥 𝑓(𝑥)𝑑𝑥 𝑖𝑓 𝑋 𝑖𝑠 𝑐𝑜𝑛𝑡𝑖𝑛𝑢𝑜𝑢𝑠
{−∞

where t being a real parameter assuming that the integration or summation is absolutely
convergent for some positive number h such that |𝑡| < ℎ. .
𝑡𝑋 (𝑡𝑋)2 (𝑡𝑋)𝑟
∴ 𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = 𝐸 [1 + + + ⋯.. + ⋯…]
1! 2! 𝑟!

𝑡2 𝑡𝑟
= 1 + 𝑡𝐸(𝑋) + 𝐸(𝑋 2 ) + ⋯ . . 𝐸(𝑋 𝑟 ) + ⋯ …
2! 𝑟!
𝑡2 ′ 𝑡𝑟
= 1 + 𝑡𝜇1′ + 𝜇2 + ⋯ . . 𝜇𝑟′ + ⋯ …
2! 𝑟!
𝜇𝑟′ = 𝑟𝑡ℎ 𝑚𝑜𝑚𝑒𝑛𝑡 𝑎𝑏𝑜𝑢𝑡 𝑡ℎ𝑒 𝑜𝑟𝑖𝑔𝑖𝑛

𝐸(𝑋 𝑡 ) = ∫ 𝑥 𝑟 (𝑓(𝑥))𝑑𝑥 𝑜𝑟

= ∑ 𝑥 𝑟 𝑝(𝑥) depending upon is continuous or discrete.


𝑡𝑟
The coefficient of in 𝐸(𝑒 𝑡𝑋 ) gives 𝜇𝑟′ .
𝑟!

Note
𝑑𝑟
1. 𝜇𝑟′ = 𝑑𝑡 𝑟 [𝑀𝑋 (𝑡)]𝑡=0
2. 𝑀𝑋 (𝑡) = 𝐸[𝑒 𝑡(𝑋−𝑎 ] (𝑎𝑏𝑜𝑢𝑡 𝑥 = 𝑎).
where 𝜇𝑟′ = 𝐸[(𝑋 − 𝑎)𝑟 ] 𝑟𝑡ℎ 𝑚𝑜𝑚𝑒𝑛𝑡 𝑎𝑏𝑜𝑢𝑡 𝑡ℎ𝑒 𝑝𝑜𝑖𝑛𝑡 𝑥 = 𝑎
3. 𝑀𝑒𝑎𝑛 = 𝑋̅
𝑡 𝑡 2 𝑡 𝑟
𝑀𝑋 (𝑡)[𝑎𝑏𝑜𝑢𝑡 𝑋 = 𝑋̅] = 1 + 1! 𝜇1 + 2! 𝜇2 + ⋯ . . 𝑟! 𝜇𝑟 + ⋯ …
where 𝜇𝑟 = 𝐸[(𝑋 − 𝑋̅)𝑟 ] = 𝑟𝑡ℎ 𝑐𝑒𝑛𝑡𝑟𝑎𝑙 𝑚𝑜𝑚𝑒𝑛𝑡 .

Properties of Moment Generating Function

1. Let 𝑌 = 𝑎𝑋 + 𝑏 , where 𝑋 is a random variable with moment generating function 𝑀𝑋 (𝑡).

Then
𝑀𝑌 (𝑡) = 𝐸[𝑒 𝑡𝑌 ]

= 𝐸[𝑒 𝑡(𝑎𝑋+𝑏) ]

= 𝐸[𝑒 𝑡𝑎𝑋 𝑒 𝑏𝑡 ]

= 𝑒 𝑏𝑡 𝐸[𝑒 𝑋𝑎𝑡 ]

= 𝑒 𝑏𝑡 𝑀𝑋 (𝑎𝑡)

2. 𝑀𝑐𝑋 (𝑡) = 𝐸[𝑒 𝑐𝑡𝑋 ] = 𝐸[𝑒 𝑋(𝑐𝑡) ] = 𝑀𝑋 (𝑐𝑡).

3. if 𝑋 and 𝑌 are two independent random variables, then 𝑀𝑋+𝑌 (𝑡) = 𝑀𝑋 (𝑡). 𝑀𝑌 (𝑡).
Proof:

𝑀𝑋+𝑌 (𝑡) = 𝐸[𝑒 𝑡(𝑋+𝑌) ]

= 𝐸[𝑒 𝑡𝑋+𝑡𝑌 ]

= 𝐸[𝑒 𝑡𝑋 𝑒 𝑡𝑌 ]
= 𝐸[𝑒 𝑡𝑋 ]𝐸[𝑒 𝑡𝑌 ] [∵ 𝑋 𝑎𝑛𝑑 𝑌 𝑎𝑟𝑒 𝑖𝑛𝑑𝑒𝑝𝑒𝑛𝑑𝑒𝑛𝑡]

= 𝑀𝑋 (𝑡). 𝑀𝑌 (𝑡).

4. If 𝑋1 , 𝑋2 , … … . 𝑋𝑛 are n independent random variables then, 𝑀𝑋1+𝑋2+,…….+𝑋𝑛 (𝑡) =


𝑀𝑋1 (𝑡)𝑀𝑋2 (𝑡) … . . 𝑀𝑋𝑛 (𝑡)

Proof:

𝑀𝑋1+𝑋2+,…….+𝑋𝑛 (𝑡) = 𝐸(𝑒 (𝑋1+𝑋2+,…….+𝑋𝑛 )𝑡 )

= 𝐸(𝑒 𝑋1𝑡 𝑒 𝑋2𝑡 … … . 𝑒 𝑋𝑛𝑡 )

= 𝐸(𝑒 𝑋1𝑡 )𝐸(𝑒 𝑋3𝑡 ) … … 𝐸(𝑒 𝑋𝑛𝑡 )[∵ 𝑋𝑖′ 𝑠 𝑎𝑟𝑒 𝑖𝑛𝑑𝑒𝑝𝑒𝑛𝑑𝑒𝑛𝑡]

= 𝑀𝑋1 (𝑡)𝑀𝑋2 (𝑡) … . . 𝑀𝑋𝑛 (𝑡)

PROBLEMS IN DISCRETE RANDOM VARIABLES

1. Determine the constant 𝒌 , given the following probability distribution of discrete


random variable 𝑿. Also find mean and variance.

𝑿 𝟏 𝟐 𝟑 𝟒 𝟓 𝑻𝒐𝒕𝒂𝒍
𝒑(𝒙) 𝟎. 𝟏 𝟎. 𝟐 𝒌 𝟐𝒌 𝟎. 𝟏 𝟏. 𝟎

Solution:
(i) To find the value of 𝒌
We know that ∑𝑛𝑖=1 𝑝(𝑥) = 1

⇒ 0.1 + 0.2 + 𝑘 + 2𝑘 + 0.1 = 1

3𝑘 + 0.4 = 1

3𝑘 = 1 − 0.4

3𝑘 = 0.6

𝒌 = 𝟎. 𝟐
So the probability distribution is given by

𝑿 𝟏 𝟐 𝟑 𝟒 𝟓 𝑻𝒐𝒕𝒂𝒍
𝒑(𝒙) 𝟎. 𝟏 𝟎. 𝟐 𝟎. 𝟐 𝟎. 𝟒 𝟎. 𝟏 𝟏. 𝟎

We Know that 𝑴𝒆𝒂𝒏 = 𝑬(𝑿) = ∑ 𝒙𝒊 𝒑(𝒙𝒊 )

𝟐
𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 𝑬(𝑿𝟐 ) − (𝑬(𝑿))

Where
𝑬(𝑿𝟐 ) = ∑ 𝒙𝟐𝒊 𝒑(𝒙𝒊 )

𝒙𝒊 𝒑(𝒙𝒊 ) 𝒙𝒊 𝒑(𝒙𝒊 ) 𝒙𝟐𝒊 𝒙𝟐𝒊 𝒑(𝒙𝒊 )


1 0.1 0.1 1 0.1
2 0.2 0.4 4 0.8
3 0.2 0.6 9 1.8
4 0.4 1.6 16 6.4
5 0.1 0.5 25 2.5

𝑬(𝒙) = ∑ 𝒙𝒊 𝒑(𝒙𝒊 ) = 𝟑. 𝟐 𝑬(𝒙𝟐 ) = ∑ 𝒙𝟐𝒊 𝒑(𝒙𝒊 ) = 𝟏𝟏. 𝟔

∴ 𝑀𝑒𝑎𝑛 = 𝐸(𝑋) = ∑ 𝑥𝑖 𝑝(𝑥𝑖 ) = 3.2

2
𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝐸(𝑋 2 ) − (𝐸(𝑋))

= 11.6 − (3.2)2

= 11.6 − 10.24

= 1.36
∴ 𝒌 = 𝟎. 𝟐

𝑴𝒆𝒂𝒏 = 𝟑. 𝟐

𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 𝟏. 𝟑𝟔
2. A random variable 𝑿 has the following probability function

𝑿 𝟎 𝟏 𝟐 𝟑 𝟒 𝟓 𝟔 𝟕 𝟖
𝒑(𝒙) 𝒂 𝟑𝒂 𝟓𝒂 𝟕𝒂 𝟗𝒂 𝟏𝟏𝒂 𝟏𝟑𝒂 𝟏𝟓𝒂 𝟏𝟕𝒂

(i) Determine the value of ′𝒂′.


(ii) Find 𝑷(𝑿 < 3) , 𝑷(𝑿 ≥ 𝟑), 𝑷(𝟎 < 𝑿 < 5).
(iii) Find the distribution function of 𝑿.

Solution:

(𝒊 ) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒂

We know that if 𝑝(𝑥) is the probability mass function, then ∑𝑛𝑖=1 𝑝(𝑥) = 1

⇒ 𝑎 + 3𝑎 + 5𝑎 + 7𝑎 + 9𝑎 + 11𝑎 + 13𝑎 + 15𝑎 + 17𝑎 = 1


81𝑎 = 1

𝟏
𝒂=
𝟖𝟏

So the given probability distribution is given by

𝑿 𝟎 𝟏 𝟐 𝟑 𝟒 𝟓 𝟔 𝟕 𝟖
𝒑(𝒙) 𝟏 𝟑 𝟓 𝟕 𝟗 𝟏𝟏 𝟏𝟑 𝟏𝟓 𝟏𝟕
𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏 𝟖𝟏

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝑿 < 3)

𝑃(𝑋 < 3) = 𝑃(0) + 𝑃(1) + 𝑃(2)

1 3 5
= + +
81 81 81

9
=
81

1
=
9

𝟏
∴ 𝑷(𝑿 < 3) =
𝟗
(𝒊𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝑿 ≥ 𝟑)

𝑃(𝑋 ≥ 3) = 1 − 𝑃(𝑋 < 3)

1
=1−
9

8
=
9

𝟖
∴ 𝑷(𝑿 ≥ 𝟑) =
𝟗

(𝒊𝒗) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝟎 < 𝑿 < 5)

𝑃(0 < 𝑋 < 5) = 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4)

3 5 7 9
= + + +
81 81 81 81

24
=
81

𝟐𝟒
∴ 𝑷(𝟎 < 𝑿 < 5) =
𝟖𝟏

(v) To find the distribution function of X


𝒙 𝒑(𝒙) 𝑭(𝒙) = 𝑷(𝑿 ≤ 𝒙)
0 1/81 𝐹(0) = 𝑃(0) = 1/81
1 3/81 𝐹(1) = 𝑃(0) + 𝑃(1) = 1/81 + 3/81 = 4/81
2 5/81 𝐹(2) = 𝑃(0) + 𝑃(1) + 𝑃(2) = 1/81 + 3/81 + 5/81 = 9/81
3 7/81 𝐹(3) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) = 1/81 + 3/81 + 5/81 + 7/81 = 16/81
4 9/81 𝐹(4) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4) = 1/81 + 3/81 + 5/81 + 7/81 + 9/81 = 25/81
5 11/81 𝐹(5) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4) + 𝑃(5) = 1/81 + 3/81 + 5/81 + 7/81 + 9/81 + 11/81 = 36/81
6 13/81 𝐹(6) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4) + 𝑃(5) + 𝑃(6)
= 1/81 + 3/81 + 5/81 + 7/81 + 9/81 + 11/81 + 13/81 = 49/81
7 15/81 𝐹(7) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4) + 𝑃(5) + 𝑃(6) + 𝑃(7)
= 1/81 + 3/81 + 5/81 + 7/81 + 9/81 + 11/81 + 13/81 + 15/81 = 64/81
8 17/81 𝐹(8) = 𝑃(0) + 𝑃(1) + 𝑃(2) + 𝑃(3) + 𝑃(4) + 𝑃(5) + 𝑃(6) + 𝑃(7) + 𝑃(8)
= 1/81 + 3/81 + 5/81 + 7/81 + 9/81 + 11/81 + 13/81 + 15/81 + 17/81 = 81/81 = 1

(or)
𝒙 𝒑(𝒙) 𝑭(𝒙) = 𝑷(𝑿 ≤ 𝒙)
0 1/81 𝐹(0) = 𝑃(0) = 1/81
1 3/81 𝐹(1) = 𝐹(0) + 𝑃(1) = 1/81 + 3/81 = 4/81
2 5/81 𝐹(2) = 𝐹(1) + 𝑃(2) = 4/81 + 5/81 = 9/81
3 7/81 𝐹(3) = 𝐹(2) + 𝑃(3) = 9/81 + 7/81 = 16/81
4 9/81 𝐹(4) = 𝐹(3) + 𝑃(4) = 16/81 + 9/81 = 25/81
5 11/81 𝐹(5) = 𝐹(4) + 𝑃(5) = 25/51 + 11/81 = 36/81
6 13/81 𝐹(6) = 𝐹(5) + 𝑃(6) = 36/81 + 13/81 = 49/81
7 15/81 𝐹(7) = 𝐹(6) + 𝑃(7) = 49/81 + 15/81 = 64/81
8 17/81 𝐹(8) = 𝐹(7) + 𝑃(8) = 64/81 + 17/81 = 81/81 = 1

3. If the random variable 𝑿 takes the value 𝟏, 𝟐, 𝟑 and 𝟒 such that


𝟐𝑷(𝑿 = 𝟏) = 𝟑𝑷(𝑿 = 𝟐) = 𝑷(𝑿 = 𝟑) = 𝟓𝑷(𝑿 = 𝟒). Find the probability
distribution.
Solution:
Let 2𝑃(𝑋 = 1) = 3𝑃(𝑋 = 2) = 𝑃(𝑋 = 3) = 5𝑃(𝑋 = 4) = 𝑘
2𝑃(𝑋 = 1) = 𝑘 ⇒ 𝑷(𝑿 = 𝟏) = 𝒌/𝟐
3𝑃(𝑋 = 2) = 𝑘 ⇒ 𝑷(𝑿 = 𝟐) = 𝒌/𝟑
𝑃(𝑋 = 3) = 𝒌
5𝑃(𝑋 = 4) = 𝑘 ⇒ 𝑷(𝑿 = 𝟒) = 𝒌/𝟓

We know that if 𝑝(𝑥) is the probability mass function, then ∑𝑛𝑖=1 𝑝(𝑥) = 1

𝒌 𝒌 𝒌
⇒ + +𝑘+ =1
𝟐 𝟑 𝟓
15𝑘+10𝑘+30𝑘+6𝑘
⇒ =1
30
61𝑘
⇒ =1
30

𝟑𝟎
∴𝒌=
𝟔𝟏

𝑘 30 15
∴ 𝑃(𝑋 = 1) = = =
2 61∗2 61

𝑘 30 10
𝑃 (𝑋 = 2) = = =
3 61∗3 61

30
𝑃(𝑋 = 3) = 61

𝑘 30 6
𝑃(𝑋 = 4) = 5 = 61∗5 = 61

∴ the probability distribution of X is given by the following data


𝑿 𝟏 𝟐 𝟑 𝟒
𝒑(𝒙) 𝟏𝟓 𝟏𝟎 𝟑𝟎 𝟔
𝟔𝟏 𝟔𝟏 𝟔𝟏 𝟔𝟏

4. If 𝑿 is discrete random variable and has the following distribution function


𝟎 ;𝒙 < 1
𝟏
;𝟏 ≤ 𝒙 < 4
𝟑
𝟏
𝑭[𝒙] = ;𝟒 ≤ 𝒙 < 6
𝟐
𝟓
; 𝟔 ≤ 𝒙 < 10
𝟔
{ 𝟏 ; 𝒙 ≥ 𝟏𝟎
Find (i) the probability distribution of 𝑿.
(ii) 𝑷(𝟐 < 𝑋 < 6).
(iii) Mean of 𝑿.
(iv) Variance of 𝑿.

Solution:

The given function can be written as

𝒙 𝟎 𝟏 𝟐 𝟑 𝟒 𝟓 𝟔 𝟕 𝟖 𝟗 𝟏𝟎
𝑭(𝒙) 𝟎 𝟏 𝟏 𝟏 𝟏 𝟏 𝟓 𝟓 𝟓 𝟓 𝟏
𝟑 𝟑 𝟑 𝟐 𝟐 𝟔 𝟔 𝟔 𝟔
(𝒗) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒅𝒊𝒔𝒕𝒓𝒊𝒃𝒖𝒕𝒊𝒐𝒏 𝒇𝒖𝒏𝒄𝒕𝒊𝒐𝒏 𝒐𝒇 𝑿

𝒙 𝑭(𝒙) 𝒑(𝒙𝒊 ) 𝒑(𝒙𝒊 ) 𝒙𝒊 𝒑(𝒙𝒊 ) 𝒙𝟐𝒊 𝒙𝟐𝒊 𝒑(𝒙𝒊 )


0 0 𝑃(0) = 𝐹(0) = 0 0 0 0 0
1 1/3 𝑃(1) = 𝐹(1) − 𝐹(0) = 1/3 − 0 = 1/3 1/3 1/3 1 1/3
2 1/3 𝑃(2) = 𝐹(2) − 𝐹(1) = 1/3 − 1/3 = 0 0 0 4 0
3 1/3 𝑃(3) = 𝐹(3) − 𝐹(2) = 1/3 − 1/3 = 0 0 0 9 0
4 1/2 𝑃(4) = 𝐹(4) − 𝐹(3) = 1/2 − 1/3 = 1/6 1/6 2/3 16 8/3
5 1/2 𝑃(5) = 𝐹(5) − 𝐹(4) = 1/2 − 1/2 = 0 0 0 25 0
6 5/6 𝑃(6) = 𝐹(6) − 𝐹(5) = (5/6) − (1/2) 1/3 2 36 12
= (10 − 6)/12 = 4/12
= 1/3
7 5/6 𝑃(7) = 𝐹(7) − 𝐹(6) = 5/6 − 5/6 = 0 0 0 49 0
8 5/6 𝑃(8) = 𝐹(8) − 𝐹(7) = 5/6 − 5/6 = 0 0 0 64 0
9 5/6 𝑃(9) = 𝐹(9) − 𝐹(8) = 5/6 − 5/6 = 0 0 0 81 0
10 1 𝑃(10) = 𝐹(10) − 𝐹(9) = 1 − 5/6 = 1/6 1/6 5/3 100 50/3
𝑬(𝑿) = ∑ 𝒙𝒊 𝒑(𝒙𝒊 ) = 𝟏𝟒/𝟑 𝑬(𝑿𝟐 ) = ∑ 𝒙𝟐𝒊 𝒑(𝒙𝒊 ) = 𝟗𝟓/𝟑
𝒙 𝟎 𝟏 𝟐 𝟑 𝟒 𝟓 𝟔 𝟕 𝟖 𝟗 𝟏𝟎
𝒑(𝒙) 𝟎 𝟏 0 𝟎 𝟏 𝟎 𝟏 𝟎 𝟎 𝟎 𝟏
𝟑 𝟔 𝟑 𝟔

∴ 𝑀𝑒𝑎𝑛 = 𝐸(𝑋) = ∑ 𝑥𝑖 𝑝(𝑥𝑖 ) = 14/3

2
𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝐸(𝑋 2 ) − (𝐸(𝑋))

= 95/3 − (14/3)2

= 89/9

𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝟐 < 𝑿 < 6)

𝑃(2 < 𝑋 < 6) = 𝑃(3) + 𝑃(4) + 𝑃(5)

1
=0+ +0
6

1
=
6

𝟏
∴ 𝑷(𝟐 < 𝑿 < 6) =
𝟔

𝑴𝒆𝒂𝒏 = 14/3

𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 89/9

𝟏
𝑷(𝟐 < 𝑿 < 6) =
𝟔

5. For the following probability distribution


(i) Find the distribution function of 𝑿.
(ii) What is the smallest value of 𝑿 for which 𝑷(𝑿 ≤ 𝒙) > 0.5.

𝑿 𝟎 𝟏 𝟐
𝒑(𝒙) 𝟏 𝟐 𝟏
𝟒 𝟒 𝟒
Solution:

𝒙 𝒑(𝒙) 𝑭(𝒙) = 𝑷(𝑿 ≤ 𝒙)


0 1/4 𝐹(0) = 𝑃(0) = 1/4 = 0.25
1 2/4 𝐹(1) = 𝐹(0) + 𝑃(1) = 1/4 + 2/4 = 3/4
= 0.75
2 ¼ 𝐹(2) = 𝐹(1) + 𝑃(2) = 3/4 + 1/4 = 1

The smallest value of 𝑥 for which 𝑃(𝑋 ≤ 𝑥) > 0.5 is 1.

Similarly 𝑃(𝑋 ≤ 𝑥) > 0.1 is 0.

𝑃(𝑋 ≤ 𝑥) > 0.8 is 2.

6. Obtain the probability function (or) probability distribution from the following
distribution function.

𝑿 𝟎 𝟏 𝟐 𝟑
𝑭(𝒙) 𝟎. 𝟏 𝟎. 𝟒 𝟎. 𝟗 𝟏. 𝟎
Solution:

Given 𝐹(𝑥). Now to find 𝑝(𝑥)

𝒙 𝑭(𝒙) 𝒑(𝒙𝒊 ) 𝒑(𝒙𝒊 )


0 0.1 𝑃(0) = 𝐹(0) = 0.1 0.1
1 0.4 𝑃(1) = 𝐹(1) − 𝐹(0) = 0.4 − 0.1 = 0.3 0.3
2 0.9 𝑃(2) = 𝐹(2) − 𝐹(1) = 0.9 − 0.4 = 0.5 0.5
3 1.0 𝑃(3) = 𝐹(3) − 𝐹(2) = 1 − 0.9 = 0.1 0.1

The probability distribution function is

𝑿 𝟎 𝟏 𝟐 𝟑 Total
𝒑(𝒙) 𝟎. 𝟏 𝟎. 𝟑 𝟎. 𝟓 𝟎. 𝟏 𝟏

7. Suppose 𝑿 is a discrete random variable such that 𝑷(𝑿 = 𝟎) = 𝟏 − 𝑷(𝑿 = 𝟏) and


𝑬(𝑿) = 𝟑𝑽𝒂𝒓(𝑿). Find 𝑷(𝑿 = 𝟎) 𝒂𝒏𝒅 𝑷(𝑿 = 𝟏).

Solution:
Given 𝑃(𝑋 = 0) = 1 − 𝑃(𝑋 = 1)
𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) = 1
∴ 𝑋 has values 0 and 1.
Let 𝑃(𝑋 = 0) = 𝑎 and 𝑃(𝑋 = 1) = 1 − 𝑎

𝑥𝑖 𝑝(𝑥) 𝑥𝑖 𝑝(𝑥𝑖 ) 𝑥𝑖2 𝑥𝑖2 𝑝(𝑥𝑖 )


0 𝑎 0 0 0
1 1−𝑎 1−𝑎 1 1−𝑎

𝑬(𝑿) = ∑ 𝒙𝒊 𝒑(𝒙𝒊 ) = 𝟏 − 𝒂 𝑬(𝑿𝟐 ) = ∑ 𝒙𝟐𝒊 𝒑(𝒙𝒊 ) = 𝟏 − 𝒂

∴ 𝑀𝑒𝑎𝑛 = 𝐸(𝑋) = ∑ 𝑥𝑖 𝑝(𝑥𝑖 ) = 1 − 𝑎

2
𝑉𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝐸(𝑋 2 ) − (𝐸(𝑋))

= (1 − 𝑎) − (1 − 𝑎)2

= (1 − 𝑎) − (12 − 2 ∗ 1 ∗ 𝑎 + 𝑎2 )

= 1 − 𝑎 − 1 + 2𝑎 − 𝑎2
= 𝑎 − 𝑎2

𝑴𝒆𝒂𝒏 = 𝟏 − 𝒂 , 𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 𝒂 − 𝒂𝟐

Given 𝐸(𝑋) = 3𝑉𝑎𝑟(𝑋)


1 − 𝑎 = 3(𝑎 − 𝑎2 )
1 − 𝑎 = 3𝑎(1 − 𝑎)
1 = 3𝑎

𝟏
∴𝒂=
𝟑

𝟏 𝟏
∴ 𝑃(𝑋 = 0) = 𝑎 = 𝟑 ⇒ 𝑃(𝑋 = 0) = 𝟑 .
𝟏 𝟐 𝟐
𝑃(𝑋 = 1) = 1 − 𝑎 = 𝟏 − 𝟑 = 𝟑 ⇒ 𝑃(𝑋 = 1) = 𝟑

∴ the probability distribution is


𝑿 𝟎 𝟏
𝒑(𝒙) 𝟏 𝟐
𝟑 𝟑
8. A shipment of 6 television sets contains two defective sets. A hotel makes a random
purchase of 3 of the sets. If 𝑿 is the number of defective sets purchased by the hotel.
Find
(i) Probability distribution of 𝑿.
(ii) Distribution function

and hence, find the probability of purchasing at the most 1 defective set and probability
of purchasing at least 1 defective sets.

Solution:

The hotel purchased 3 TV sets out of 6 which contains 2 defective.

Let 𝑋 = Number of defective sets purchased.

𝑃(𝑋 = 𝑥) = P [choosing exactly r defective sets]

= P [choosing r defective and (3-r) good sets]

4.3.2
2𝐶0 ∗ 4𝐶3 1 ∗ 1.2.3 4 1
𝑃(𝑋 = 0) = = = =
6𝐶3 6.5.4 20 5
1.2.3
4.3
2𝐶1 ∗ 4𝐶2 2 ∗ 1.2 12 3
𝑃(𝑋 = 1) = = = =
6𝐶3 6.5.4 20 5
1.2.3
2𝐶2 ∗ 4𝐶1 1∗4 4 1
𝑃(𝑋 = 2) = = = =
6𝐶3 6.5.4 20 5
1.2.3
(i) The probability distribution function is

𝑿 𝟎 𝟏 𝟐 Total
𝒑(𝒙) 𝟏 𝟑 𝟏 𝟏
𝟓 𝟓 𝟓

𝒙 𝒑(𝒙) 𝑭(𝒙) = 𝑷(𝑿 ≤ 𝒙)


0 1/5 𝐹(0) = 𝑃(0) = 1/5
1 3/5 𝐹(1) = 𝐹(0) + 𝑃(1) = 1/5 + 3/5 = 4/5
2 1/5 𝐹(2) = 𝐹(1) + 𝑃(2) = 1/5 + 4/5 = 1
(ii) The distribution function is

𝑿 𝟎 𝟏 𝟐
𝑭(𝒙) 𝟏 𝟒 𝟏
𝟓 𝟓
(𝒊𝒊𝒊) 𝑷[ 𝒂𝒕 𝒎𝒐𝒔𝒕 𝒐𝒏𝒆 𝒅𝒆𝒇𝒆𝒄𝒕𝒊𝒗𝒆 ) = 𝑷(𝑿 ≤ 𝟏)
1 3 4
= 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) = 5 + 5 = 5

(𝒊𝒗) 𝑷[ 𝒂𝒕 𝒍𝒆𝒂𝒔𝒕 𝒐𝒏𝒆 𝒅𝒆𝒇𝒆𝒄𝒕𝒊𝒗𝒆 ) = 𝑷(𝑿 ≥ 𝟏)


3 1 4
= 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) = 5 + 5 = 5

9. A random experiment consist of three independent tosses of a fair coin and 𝑿 denotes the
random variables which assigns to each element 𝑾 of a sample space 𝑺, the number of heads
in 𝑾 and 𝒀 denotes the number of consecutive heads in 𝑾. Find

(i) The probability distribution of 𝑿.

(ii) The p.d.f of 𝑿 and 𝒀.

(iii)The probability table of 𝑿 + 𝒀 and 𝑿𝒀.

Solution:

The sample space of the random experiment of 3 tosses contain eight elements.

That is 𝑆 = {𝐻𝐻𝐻, 𝐻𝐻𝑇, 𝐻𝑇𝐻, 𝑇𝐻𝐻, 𝐻𝑇𝑇, 𝑇𝐻𝑇, 𝑇𝑇𝐻, 𝑇𝑇𝑇}

1 1 1 1
⇒𝑆= ∗ ∗ =
2 2 2 8

1
𝑃(𝑋 = 3) =
8

3 1 1 1
𝑃(𝑋 = 2) = 8 ( + + )
8 8 8

3 1 1 1
𝑃(𝑋 = 1) =
8
( + + )
8 8 8

1
𝑃(𝑋 = 0) = 8
Now we will construct a table:

Sno Event 𝑋 𝑌 𝑋+𝑌 𝑋𝑌


1 HHH 3 3 6 9
2 HHT 2 2 4 4
3 HTH 2 0 2 0
4 THH 2 2 4 4
5 HTT 1 0 1 0
6 THT 1 0 1 0
7 TTH 1 0 1 0
8 TTT 0 0 0 0

(𝒊𝒊) 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒕𝒂𝒃𝒍𝒆 𝒐𝒇 𝑿

𝑿 𝟎 𝟏 𝟐 𝟑
𝒑(𝒙) 𝟏 𝟑 𝟑 𝟏
𝟖 𝟖 𝟖 𝟖

(𝒊𝒊𝒊) 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒕𝒂𝒃𝒍𝒆 𝒐𝒇 𝒀

𝒀 𝟎 𝟐 𝟑
𝒑(𝒚) 𝟓 𝟐 𝟏
𝟖 𝟖 𝟖

⇒ the probability distribution of 𝑋 can be easily written from the above table
0 𝑖𝑓 𝑥 < 0
1
𝑖𝑓 0 ≤ 𝑥 < 1
8
4
𝐹(𝑥) = 𝑖𝑓 1 ≤ 𝑥 < 2
8
7
𝑖𝑓 2 ≤ 𝑥 < 3
8
{ 1 𝑖𝑓 𝑥 ≥ 3
0 𝑖𝑓 𝑥 < 0
5
𝑖𝑓 0 ≤ 𝑥 < 2
8
𝐹(𝑦) = 7
𝑖𝑓 2 ≤ 𝑥 < 3
8
1 𝑖𝑓 𝑥 ≥ 3
{

(𝒊𝒊) 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒕𝒂𝒃𝒍𝒆 𝒐𝒇 𝑿 + 𝒀 = 𝒁

𝒁 𝟎 𝟏 𝟐 𝟒 𝟔
𝒑(𝒛) 𝟏 𝟑 𝟏 𝟐 𝟏
𝟖 𝟖 𝟖 𝟖 𝟖

(𝒊𝒊) 𝑷𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒕𝒂𝒃𝒍𝒆 𝒐𝒇 𝑿𝒀 = 𝑾

𝑾 𝟎 𝟒 𝟗
𝒑(𝒘) 𝟓 𝟐 𝟏
𝟖 𝟖 𝟖

PROBLEMS IN CONTINUOUS RANDOM VARIABLES

−𝑥2
1. If 𝑓(𝑥) = { 𝑥𝑒 2 ; 𝑥 > 0 . show that 𝑓(𝑥) is a 𝑝𝑑𝑓.
0 ;𝑥 ≤ 0

Solution:


We know that the pdf of 𝑓(𝑥) is ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1

−𝑥2
Given 𝑓(𝑥) = { 𝑥𝑒 2 ; 𝑥>0
0 ;𝑥 ≤ 0

∞ 0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 = ∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥
−𝑥 2
∞ 0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 = ∫−∞ 0 ∗ 𝑑𝑥 + ∫0 𝑥𝑒 2 𝑑𝑥

∞ ∞ −𝑥2
∴ ∫0 𝑓(𝑥)𝑑𝑥 = ∫0 𝑥𝑒 2 𝑑𝑥

∞ 𝑥2 𝒙=𝟎 ; 𝒕=𝟎
= ∫0 𝑒 −𝑡 𝑑𝑡 𝑙𝑒𝑡 =𝑡 𝑤ℎ𝑒𝑛 𝒙=∞ ; 𝒕= ∞
2

2𝑥𝑑𝑥
= [−𝑒 −𝑡 ]∞
0 = 𝑑𝑡
2

2𝑥𝑑𝑥
= [0 + 1] = 𝑑𝑡
2

=1 𝑥𝑑𝑥 = 𝑑𝑡

∫ 𝑓(𝑥)𝑑𝑥 = 1
0

∴ 𝑓(𝑥) is a pdf of a continuous random variable 𝑋.

2. A continuous random variable 𝑿 that can assume any value between 𝒙 = 𝟐 and 𝒙 =
𝟓 has a density function given by 𝒇(𝒙) = 𝒌(𝟏 + 𝒙). Find 𝑷(𝑿 < 4).
Solution:

(i) We know that ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1.

Given 𝑓(𝑥) = 𝑘(1 + 𝑥)


∞ 2 5 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 = ∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫2 𝑓(𝑥)𝑑𝑥 + ∫5 𝑓(𝑥)𝑑𝑥 = 1

2 5 ∞
∫−∞ 0𝑑𝑥 + ∫2 𝑓(𝑥)𝑑𝑥 + ∫5 0𝑑𝑥 = 1

5
∴ ∫2 𝑓(𝑥)𝑑𝑥 = 1

5
∫2 𝑘(1 + 𝑥)𝑑𝑥 = 1

5
𝑘 [∫2 (1 + 𝑥)𝑑𝑥] = 1

5 5
𝑘 [∫2 𝑑𝑥 + ∫2 𝑥𝑑𝑥 ] = 1

5
𝑥2
𝑘 [[𝑥]52 + [ 2 ] ] = 1
2
25 4
𝑘 [[5 − 2] + [ 2 − 2]] = 1

25
𝑘 [[3] + [ 2 − 2]] = 1

21
𝑘 [3 + ]=1
2

27
𝑘[2] = 1

2
∴ 𝑘 = 27

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝑿 < 4) 0 𝑓(𝑥) 0

4
𝑃(𝑋 < 4) = ∫2 𝑓(𝑥)𝑑𝑥 −∞ 2 4 5 ∞

4
= ∫2 𝑘(1 + 𝑥)𝑑𝑥

4
= 𝑘 [∫2 (1 + 𝑥)𝑑𝑥]

2 4 4
= 27 [∫2 𝑑𝑥 + ∫2 𝑥𝑑𝑥]

4
2 𝑥2
= 27 [[𝑥]42 + [ 2 ] ]
2

2 16 4
= 27 [[4 − 2] + [ 2 − 2]]

2
= 27 [[2] + [8 − 2]]

2
= 27 [2 + 6]

16
= 27

𝟏𝟔
∴ 𝑷(𝑿 < 4) = 𝟐𝟕

3. A continuous RV 𝑿 has a density function given by


𝑓(𝑥) = 𝑘𝑥 2 𝑒 −𝑥 ; 0 < 𝑋 < ∞ and find mean and variance of the distribution.
Solution:


(i) We know that ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1.

Given 𝑓(𝑥) = 𝑘𝑥 2 𝑒 −𝑥
∞ 0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 = ∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1

0 ∞
∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1


∴ ∫0 𝑓(𝑥)𝑑𝑥 = 1


∫0 𝑘𝑥 2 𝑒 −𝑥 𝑑𝑥 = 1


𝑘[∫0 𝑥 2 𝑒 −𝑥 𝑑𝑥] = 1 0 𝑓(𝑥)

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3+⋯.. −∞ 0 ∞

𝑘[−𝑥 2 𝑒 −𝑥 + 2𝑥𝑒 −𝑥 − 2𝑒 −𝑥 ]∞
0 =1 let 𝑢 = 𝑥 2 𝑑𝑣 = 𝑒 −𝑥

𝑘[0 − (0 + 0 − 2)] = 1 𝑢′ = 2𝑥 𝑣 = −𝑒 −𝑥

2𝑘 = 1 𝑢′′ = 2 𝑣1 = 𝑒 −𝑥
𝟏
∴𝒌= 𝟐
𝑢′′′ = 0 𝑣2 = −𝑒 −𝑥

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑴𝒆𝒂𝒏 𝑬(𝑿)


We know that ∫−∞ 𝑥𝑓(𝑥)𝑑𝑥

∞ 0 ∞
∫−∞ 𝑥𝑓(𝑥)𝑑𝑥 = ∫−∞ 𝑥𝑓(𝑥)𝑑𝑥 + ∫0 𝑥𝑓(𝑥)𝑑𝑥

0 ∞
= ∫−∞ 0𝑑𝑥 + ∫0 𝑥𝑓(𝑥)𝑑𝑥


= ∫0 𝑥𝑘𝑥 2 𝑒 −𝑥 𝑑𝑥


= ∫0 𝑘𝑥 3 𝑒 −𝑥 𝑑𝑥


= 𝑘 ∫0 𝑥 3 𝑒 −𝑥 𝑑𝑥
1 ∞
= 2 ∫0 𝑥 3 𝑒 −𝑥 𝑑𝑥

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3+⋯..

1
= 2 [−𝑥 3 𝑒 −𝑥 − 3𝑥 2 𝑒 −𝑥 − 6𝑥𝑒 −𝑥 − 6𝑒 −𝑥 ]∞
0

let 𝑢 = 𝑥 3 𝑑𝑣 = 𝑒 −𝑥

1
= 2 [0 − (0 − 0 − 0 − 6)] 𝑢′ = 3𝑥 2 𝑣 = −𝑒 −𝑥

1
=2∗6 𝑢′′ = 3𝑥 𝑣1 = 𝑒 −𝑥

=3 𝑢′′′ = 3 𝑣2 = −𝑒 −𝑥

∴ 𝑬(𝑿) = 𝟑 𝑢′′′′ = 0 𝑣3 = 𝑒 −𝑥

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆


𝟐
We know that 𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 𝑬(𝑿𝟐 ) − (𝑬(𝑿))


To find 𝐸(𝑋 2 ) = ∫−∞ 𝑥 2 𝑓(𝑥)𝑑𝑥

∞ 0 ∞
∫−∞ 𝑥 2 𝑓(𝑥)𝑑𝑥 = ∫−∞ 𝑥 2 𝑓(𝑥)𝑑𝑥 + ∫0 𝑥 2 𝑓(𝑥)𝑑𝑥

0 ∞
= ∫−∞ 0𝑑𝑥 + ∫0 𝑥 2 𝑓(𝑥)𝑑𝑥


= ∫0 𝑥 2 𝑘𝑥 2 𝑒 −𝑥 𝑑𝑥


= ∫0 𝑘𝑥 4 𝑒 −𝑥 𝑑𝑥


= 𝑘 ∫0 𝑥 4 𝑒 −𝑥 𝑑𝑥

1 ∞
= 2 ∫0 𝑥 4 𝑒 −𝑥 𝑑𝑥

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3 + 𝑢′𝑣 𝑣4 − ⋯ ..

1
= 2 [−𝑥 4 𝑒 −𝑥 − 4𝑥 3 𝑒 −𝑥 − 12𝑥 2 𝑒 −𝑥 − 24𝑥𝑒 −𝑥 − 24𝑒 −𝑥 ]∞
0
Let 𝑢 = 𝑥 4 𝑑𝑣 = 𝑒 −𝑥

1
= 2 [0 − (0 − 0 − 0 − 0 − 24)] 𝑢′ = 4𝑥 3 𝑣 = −𝑒 −𝑥

1
= 2 ∗ 24 𝑢′′ = 12𝑥 2 𝑣1 = 𝑒 −𝑥

= 12 𝑢′′′ = 24𝑥 𝑣2 = −𝑒 −𝑥

∴ 𝑬(𝑿𝟐 ) = 𝟏𝟐 𝑢𝑖𝑣 = 24 𝑣3 = 𝑒 −𝑥

𝑢𝑣 = 0 𝑣4 = −𝑒 −𝑥

𝟐
𝑽𝒂𝒓𝒊𝒂𝒏𝒄𝒆 = 𝑬(𝑿𝟐 ) − (𝑬(𝑿))

= 12 − (3)2

= 12 − 9

=3

∴ 𝑽𝒂𝒓(𝑿) = 𝟑

4. A continuous RV 𝑿 has a density function given by 𝒇(𝒙) = 𝟑𝒙𝟐 ; 𝟎 ≤ 𝑋 ≤ 𝟏. Find a and b


such that (𝒊) 𝑷(𝑿 ≤ 𝒂) = 𝑷(𝑿 > 𝑎) and (𝒊𝒊) 𝑷(𝑿 > 𝒃) = 𝟎. 𝟎𝟓.

Solution:

(i)To find 𝑷(𝑿 ≤ 𝒂) = 𝑷(𝑿 > 𝑎) 0 𝑎 1

𝑎 1
∫0 𝑓(𝑥)𝑑𝑥 = ∫𝑎 𝑓(𝑥)𝑑𝑥

𝑎 1
∫0 3𝑥 2 𝑑𝑥 = ∫𝑎 3𝑥 2 𝑑𝑥
𝑎 1
3𝑥 3 3𝑥 3
[ ] =[ ]
3 0 3 𝑎

[ 𝑥 3 ]𝑎0 = [𝑥 3 ]1𝑎

[𝑎3 − 0] = [1 − 𝑎3 ]

𝑎3 = 1 − 𝑎3

2𝑎3 = 1

1 3
1 ∴ 𝒂 = 𝟎. 𝟕𝟗𝟑𝟕
𝑎= ( )
2

(ii) To find 𝑷(𝑿 > 𝒃) = 𝟎. 𝟎𝟓 0 𝑏 1

1
𝑃(𝑋 > 𝑏) = ∫𝑏 𝑓(𝑥)𝑑𝑥

1
𝑃(𝑋 > 𝑏) = ∫𝑏 3𝑥2 𝑑𝑥

1
3𝑥 3
=[ ]
3 𝑏

0.05 = [1 − 𝑏 3 ]

𝑏 3 = 1 − 0.05

𝑏 3 = 0.95

1 ∴ 𝒃 = 𝟎. 𝟗𝟖𝟑𝟎
𝑏 = (0.95)3

𝟎 ;𝒙 ≤ 𝟎
5. If a RV 𝑿 has a continuous distribution function given by 𝑭(𝒙) = { .
𝒄(𝟏 − 𝒆−𝒙 ) ; 𝒙 > 0
Find (𝒊) 𝒑𝒅𝒇 𝒐𝒇 𝒇(𝒙) , (𝒊𝒊) 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒄 and (𝒊𝒊𝒊) 𝑷(𝟏 < 𝑋 < 2).

Solution:

(𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒑𝒅𝒇 𝒐𝒇 𝒇(𝒙)

𝑑
𝑤𝑒 𝑘𝑛𝑜𝑤 𝑡ℎ𝑎𝑡 𝑓(𝑥) = 𝑑𝑥
𝐹(𝑥) = 𝐹 ′ (𝑥) −∞ 0 ∞

0 ;𝑥 ≤ 0
⇒ 𝐹 ′ (𝑥) = {
𝑐𝑒−𝑥 ; 𝑥 > 0
0 ;𝑥 ≤ 0
⇒ 𝑓(𝑥) = {
𝑐𝑒−𝑥 ; 𝑥 > 0

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒄


We know that ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1
0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1
0 ∞
∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1

∫0 𝑐𝑒 −𝑥 𝑑𝑥 = 1

𝑒 −𝑥 ∞
𝑐[ ] =1
−1 0

𝑐[0 + 1] = 1

∴𝒄= 𝟏

(𝒊𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷(𝟏 < 𝑋 < 2)

∞ 2 2 𝑒−𝑥 2
∫−∞ 𝑓(𝑥)𝑑𝑥 = ∫1 𝑐𝑒−𝑥 𝑑𝑥 = ∫1 𝑒−𝑥 𝑑𝑥 = [ ]
−1 1
= −[𝑒−2 − 𝑒−1 ] = [𝑒−1 − 𝑒−2 ].

6. Suppose that the life length of a certain radio tube ( n hours)is a continuous random
𝟏𝟎𝟎
;𝒙 ≥ 𝟎
variable 𝑿 with pdf 𝒇(𝒙) = { 𝒙𝟐 .
𝟎 ; 𝒆𝒍𝒔𝒆𝒘𝒉𝒆𝒓𝒆
(i) What is the probability that a tube will last less than 200hr if it is know that tube
is still functioning after 150hr of service?
(ii) What is the probability that if such three tubes are installed in a set, exactly 1
will have to be replaced after 150hr of service?
(iii) What is the maximum number of tubes that may be inserted into a set so that
there is a probability of 0.1that after 150hr of service all of them still
functioning?
Solution:
Given 𝑋 - life length of a radio tube (in hours) is a continuous random variable
100
;𝑥 ≥ 0
having pdf 𝑓(𝑥) = { 𝑥2 (1)
0 ; 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
(i) P[ tube will last less than 200hr if it is know that tube is still functioning
after 150hr of service] ie/.. conditional probability.
𝑃[𝐴 ∩ 𝐵]
𝑤𝑒 𝑘𝑛𝑜𝑤 𝑡ℎ𝑎𝑡 𝑃[𝐴/𝐵] =
𝑃[𝐵]

𝑃[[𝑋<200]∩[𝑋>150]]
𝑃[𝑋 < 200/𝑋 > 150] = 𝑃[𝑋>150]

𝑃[150<𝑋<200]
∴ 𝑃[𝑋 < 200/𝑋 > 150] = (2)
𝑃[150<𝑋<∞]

200 100
𝐴𝑙𝑠𝑜 𝑃[150 < 𝑋 < 200] = ∫150 𝑑𝑥
𝑥2

200 1
= 100 ∫150 𝑑𝑥
𝑥2

−1 200
= 100 [ 𝑥 ]
150

1 1
= −100 [200 − 150]

3−4
= −100 [ 600 ]

−1
= −100 [ ]
600

1
𝑃[150 < 𝑋 < 200] = 6

∞ 100
Now 𝑃[150 < 𝑋 < ∞] = ∫150 𝑑𝑥
𝑥2


1
= 100 ∫ 𝑑𝑥
𝑥2
150

−1 ∞
= 100 [ 𝑥 ]
150

1
= −100 [0 − ]
150

100
=
150

2
𝑃[150 < 𝑋 < ∞] = 3
𝑃[150 < 𝑋 < 200] 1/6 1
(2) ⇒ 𝑃[𝑋 < 200/𝑋 > 150] = = =
𝑃[150 < 𝑋 < ∞] 2/3 4

2
(ii) Now we have P[ a tube is functioning after 150hr]= 𝑃[150 < 𝑋 < ∞] =
3
2
⇒ 𝑃[𝑋 > 150] = 3

∴ P[ a tube is functioning after 150hr]= 𝑃[𝑋 ≤ 150] = 1 − 𝑃[𝑋 > 150]


2 1
= 1 − 3 = 3.
∴ 3 tube being used.

P[exactly one is replaced after 150hr]= P[ one fails within 150hrs and
two are functioning after 150hr]
= 𝑃[𝑋1 < 150 ; 𝑋2 > 150 ; 𝑋3 > 150]
= 𝑃[𝑋1 < 150 ]𝑃[ 𝑋2 > 150 ]𝑃[ 𝑋3 > 150]
1 2 2 4
=3 . 3 . 3 = 27
(iii) Let there be r number of tubes so that the probability that all are
functioning after 150h is o.1
∴ P[ all r tubes are working]=0.1
2 𝑟
Ie/. (3) = 0.1
2
𝑟𝑙𝑜𝑔 3 = 𝑙𝑜𝑔0.1
𝑙𝑜𝑔0.1 −2.303
𝑟= = = 5.68.
log 0.667 −0.405
∴ The maximum number of tubes = 5.
7. The diameter of an electric cable 𝑿 is a continuous random variable with pdf
𝒇(𝒙) = 𝒌𝒙(𝟏 − 𝒙); 𝟎 ≤ 𝑿 ≤ 𝟏 . find (𝒊) 𝑭𝒊𝒏𝒅 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒌 (𝒊𝒊)𝒄𝒅𝒇 𝒐𝒇 𝑿
(𝒊𝒊𝒊) 𝑻𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒂 𝒔𝒖𝒄𝒉 𝒕𝒉𝒂𝒕 𝑷(𝑿 < 𝑎) = 𝟐𝑷(𝑿 > 𝑎)
𝟏 𝟏 𝟐
(𝒊𝒗)𝑷 [𝑿 ≤ / <𝑋< ]
𝟐 𝟑 𝟑

Solution:

(𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒌


We know that ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1
0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1
0 1
∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1
1
∫0 𝑘𝑥(1 − 𝑥)𝑑𝑥 = 1

1
𝑘 ∫0 𝑥(1 − 𝑥)𝑑𝑥 = 1

1 1
𝑘 [∫0 𝑥𝑑𝑥 − ∫0 𝑥 2 𝑑𝑥] = 1

1
𝑥2 𝑥3
𝑘[2 − ] =1
3 0

1 1
𝑘 [[2 − 3] − [0]] = 1

3−2
𝑘[ ]=1
6

𝑘
=1
6

∴𝒌= 𝟔

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒄𝒅𝒇 𝒐𝒇 𝑿

𝑥
We know that cdf of X is 𝐹(𝑥) = ∫−∞ 𝑓(𝑥)𝑑𝑥

0 𝑥
𝐹(𝑥) = ∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥

𝑥
𝐹(𝑋 ≤ 𝑥) = ∫0 6(𝑥 − 𝑥 2 )𝑑𝑥

𝑥
𝑥2 𝑥3
= 6[ − ]
2 3 0

𝑥2 𝑥3
= 6 [( − ) − (0)]
2 3

3𝑥 2 − 2𝑥 3
= 6[ ]
6

= 3𝑥 2 − 2𝑥 3 ; 0 ≤ 𝑋 ≤ 1

(𝒊𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇 𝒂 𝒔𝒖𝒄𝒉 𝒕𝒉𝒂𝒕 𝑷(𝑿 < 𝑎) = 𝟐𝑷(𝑿 > 𝑎)

Given 𝑃(𝑋 < 𝑎) = 2𝑃(𝑋 > 𝑎)


𝑎 1
∫0 6(𝑥 − 𝑥 2 )𝑑𝑥 = 2 ∫𝑎 6(𝑥 − 𝑥 2 )𝑑𝑥

𝑎 1
𝑥2 𝑥3 𝑥2 𝑥3
6[2 − ] = 12 [ 2 − ]
3 0 3 𝑎

𝑎 1
3𝑥 2 −2𝑥 3 3𝑥 2 −2𝑥 3
6[ ] = 12 [ ]
6 0 6 𝑎

[3𝑥 2 − 2𝑥 3 ]𝑎0 = 2[3𝑥 2 − 2𝑥 3 ]1𝑎

([3𝑎2 − 2𝑎3 ] − 0) = 2[[3 − 2] − [3𝑎2 − 2𝑎3 ]]

3𝑎2 − 2𝑎3 = 2[1 − 3𝑎2 + 2𝑎3 ]

3𝑎2 − 2𝑎3 = 2 − 6𝑎2 + 4𝑎3

9𝑎2 − 6𝑎3 = 2

3𝑎2 [3 − 2𝑎] = 2

2 1
3𝑎2 = 2 ⇒ 𝑎 = ±√3 ; 3 − 2𝑎 = 2 ⇒ 𝑎 = 2

𝟐 𝟏
∴ 𝒂 = ±√𝟑 ; 𝒂 = 𝟐

𝟏 𝟏 𝟐
(𝒊𝒗) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷 [𝑿 ≤ / <𝑋< ]
𝟐 𝟑 𝟑

𝑃[𝐴 ∩ 𝐵]
𝑤𝑒 𝑘𝑛𝑜𝑤 𝑡ℎ𝑎𝑡 𝑏𝑦 𝑐𝑜𝑛𝑑𝑖𝑡𝑖𝑜𝑛𝑎𝑙 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑃[𝐴/𝐵] =
𝑃[𝐵]

1 2
<𝑋<
3 3

1 1 2
1 1 2 𝑃[[𝑋≤ ]∩[ <𝑋< ]]
2 3 3
⇒ 𝑃 [𝑋 ≤ 2 / 3 < 𝑋 < 3] = 1 2 0 1/3 1/2 2/3 1
𝑃[ <𝑋< ]
3 3

1
𝑋≤2

1 1
𝑃[3<𝑋<2]
= 1 2
𝑃[3<𝑋<3]
1
1 1 2
Now 𝑃 [ < 𝑋 < ] = ∫ (𝑥 − 𝑥2 )𝑑𝑥 1 6
3 2
3

1
𝑥2 𝑥3 2
= 6[2 − ]
3 1
3

1 1 1 1
= 6 ([8 − 26] − [18 − 81])

3−1 9−2
= 6 ([ 24 ] − [ 162 −])

2 7 13
= 6 (24 − 162) = 54

2
1 2
𝑃 [ < 𝑋 < ] = ∫13 6(𝑥 − 𝑥2 )𝑑𝑥
3 3
3

2
𝑥2 𝑥3 3
= 6[2 − ]
3 1
3

4 8 1 1
= 6 ([18 − 81] − [18 − 81])

10 7 13
= 6 (81 − 162) = 27

13
1 1 2
𝑃 [[𝑋 ≤ ] ∩ [ < 𝑋 < ]] 𝑃 [1 < 𝑋 < 1] 1
3 2 = 54 =
1 1 2 2 3 3
∴ 𝑃 [𝑋 ≤ / < 𝑋 < ] = =
2 3 3 1 2
𝑃[ < 𝑋 < ] 1 2
𝑃 [3 < 𝑋 < 3 ] 13 2
3 3
27

8. Experience has shown that while walking in a certain park, the time 𝑿( in mins),
between seeing two people smoking has a density function
𝝀𝒙𝒆−𝒙 ; 𝒙 > 0
𝒇(𝒙) = { .
𝟎 ; 𝒆𝒍𝒔𝒆𝒘𝒉𝒆𝒓𝒆
(𝒊)𝑪𝒂𝒍𝒄𝒖𝒍𝒂𝒕𝒆 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇𝝀
(𝒊𝒊)𝑭𝒊𝒏𝒅 𝒕𝒉𝒆 𝒅𝒊𝒔𝒕𝒓𝒊𝒃𝒖𝒕𝒊𝒐𝒏 𝒇𝒖𝒏𝒄𝒕𝒊𝒐𝒏 𝒐𝒇 𝑿 and
(𝒊𝒊𝒊)𝑾𝒉𝒂𝒕 𝒊𝒔 𝒕𝒉𝒆 𝒑𝒓𝒐𝒃𝒂𝒃𝒊𝒍𝒊𝒕𝒚 𝒕𝒉𝒂𝒕 𝒋𝒆𝒇𝒇, 𝒘𝒉𝒐 𝒉𝒂𝒔 𝒋𝒖𝒔𝒕 𝒔𝒆𝒆𝒏 𝒂
𝒑𝒆𝒓𝒔𝒐𝒏 𝒔𝒎𝒐𝒌𝒊𝒏𝒈, 𝒘𝒊𝒍𝒍 𝒔𝒆𝒆 𝒂𝒏𝒐𝒕𝒉𝒆𝒓 𝒑𝒆𝒓𝒔𝒐𝒏 𝒔𝒎𝒐𝒌𝒊𝒏𝒈 𝒊𝒏 𝟐 𝒕𝒐 𝟓 𝒎𝒊𝒏𝒖𝒕𝒆𝒔,
𝒊𝒏 𝒂𝒕 𝒍𝒆𝒂𝒔𝒕 𝟕 𝒎𝒊𝒏𝒖𝒕𝒆𝒔.
Solution:
𝝀𝒙𝒆−𝒙 ; 𝒙 > 0
Given 𝒇(𝒙) = {
𝟎 ; 𝒆𝒍𝒔𝒆𝒘𝒉𝒆𝒓𝒆

(𝒊) 𝑻𝒐 𝒄𝒂𝒍𝒄𝒖𝒍𝒂𝒕𝒆 𝒕𝒉𝒆 𝒗𝒂𝒍𝒖𝒆 𝒐𝒇𝝀



We know that ∫−∞ 𝑓(𝑥)𝑑𝑥 = 1
0 ∞
∫−∞ 𝑓(𝑥)𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1
0 ∞
∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥 = 1

∫0 𝜆𝑥𝑒 −𝑥 𝑑𝑥 = 1

𝜆 ∫0 𝑥𝑒 −𝑥 𝑑𝑥 = 1

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3 + ⋯

let 𝑢 = 𝑥 𝑑𝑣 = 𝑒 −𝑥

𝜆[−𝑥𝑒 −𝑥 − 𝑒 −𝑥 ]∞
0 =1 𝑢′ = 1 𝑣 = −𝑒 −𝑥

𝜆[(0 − 0) − (0 − 1)] = 1 𝑢′′ = 0 𝑣1 = 𝑒 −𝑥

𝜆=1

∴𝝀= 𝟏

(𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝒕𝒉𝒆 𝒅𝒊𝒔𝒕𝒓𝒊𝒃𝒖𝒕𝒊𝒐𝒏 𝒇𝒖𝒏𝒄𝒕𝒊𝒐𝒏 𝒐𝒇 𝑿


𝑥
We know that cdf of X is 𝐹[𝑥] = ∫−∞ 𝑓(𝑥)𝑑𝑥 , 𝑥 ≥ 0

0 𝑥
𝐹(𝑥) = ∫−∞ 0𝑑𝑥 + ∫0 𝑓(𝑥)𝑑𝑥

𝑥
𝐹(𝑋 ≤ 𝑥) = ∫0 𝜆𝑥𝑒 −𝑥 𝑑𝑥

𝑥
= ∫0 𝑥𝑒 −𝑥 𝑑𝑥

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3 + ⋯ let 𝑢 = 𝑥 𝑑𝑣 = 𝑒 −𝑥

= [−𝑥𝑒 −𝑥 − 𝑒 −𝑥 ]0𝑥 𝑢′ = 1 𝑣 = −𝑒 −𝑥

= [(−𝑥𝑒 −𝑥 − 𝑒 −𝑥 ) − (0 − 1)] 𝑢′′ = 0 𝑣1 = 𝑒 −𝑥

= −𝑒 −𝑥 [𝑥 + 1] + 1

= 1 − 𝑒 −𝑥 [𝑥 + 1]

(𝒊𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷[𝟐 < 𝑋 < 5]

5
𝑃[2 < 𝑋 < 5] = ∫2 𝜆𝑥𝑒−𝑥 𝑑𝑥
5
= ∫2 𝑥𝑒−𝑥 𝑑𝑥

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3 + ⋯ let 𝑢 = 𝑥 𝑑𝑣 = 𝑒 −𝑥

= [−𝑥𝑒 −𝑥 − 𝑒 −𝑥 ]52 𝑢′ = 1 𝑣 = −𝑒 −𝑥

= [(−5𝑒 −5 − 𝑒 −5 ) − (−2𝑒 −2 − 𝑒 −2 )] 𝑢′′ = 0 𝑣1 = 𝑒 −𝑥

= 0.37

(𝒊𝒊𝒊) 𝑻𝒐 𝒇𝒊𝒏𝒅 𝑷[𝑿 ≥ 𝟕]


𝑃[𝑋 ≥ 7] = 1 − 𝑃[𝑋 < 7]


𝑃[𝑋 ≥ 7] = 1 − ∫7 𝜆𝑥𝑒−𝑥 𝑑𝑥


= 1 − ∫7 𝑥𝑒−𝑥 𝑑𝑥

We know that ∫ 𝑢𝑑𝑣 = 𝑢𝑣 − 𝑢′ 𝑣1 + 𝑢′′ 𝑣2 − 𝑢′′′ 𝑣3 + ⋯ let 𝑢 = 𝑥 𝑑𝑣 = 𝑒 −𝑥

= 1 − [−𝑥𝑒 −𝑥 − 𝑒 −𝑥 ]∞
7 𝑢′ = 1 𝑣 = −𝑒 −𝑥

= 8𝑒 −7 𝑢′′ = 0 𝑣1 = 𝑒 −𝑥

PROBLEMS IN MOMENT AND MOMENT GENERATING FUNCTIONS IN

DISCRETE AND CONTINUOUS CASE


𝟏
1. The probability function of an infinite discrete distribution is given by (𝑿 = 𝒙) = 𝟐𝒙 ,
𝒙 = 𝟏, 𝟐, 𝟑, … … … ∞. Verify that the total probability is 1 and find the MGF, mean and
variance of the distribution. Find also 𝑷(𝑿 𝒊𝒔 𝒆𝒗𝒆𝒏), 𝑷(𝑿 ≤ 𝟓) and
𝑷(𝑿 𝒊𝒔 𝒅𝒊𝒗𝒊𝒔𝒊𝒃𝒍𝒆 𝒃𝒚 𝟑).

Solution:
1
Given 𝑃(𝑋 = 𝑥) = 2𝑥 , 𝑥 = 1,2,3, … … … ∞.

To verify ∑∞
𝒙=𝟏 𝑷(𝑿 = 𝒙) = 𝟏

∑ 𝑷(𝑿 = 𝒙) = 𝑷(𝑿 = 𝟏) + 𝑷(𝑿 = 𝟐) + 𝑷(𝑿 = 𝟑) + ⋯ … . .


𝒙=𝟏

1 1 1
= + 2 + 3 + ⋯ … ..
2 2 2
1 1 1 1
= (1 + + 2 + 3 + ⋯ … . . )
2 2 2 2

1 1 −1
= (1 − ) 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−1 = 1 + 𝑥 + 𝑥 2 + ⋯ … ….
2 2

1 1 −1
= ( )
2 2
1
= (2)
2
=1

Hence verified.

To find MGF

𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = ∑ 𝑒 𝑡𝑥 𝑝(𝑥)


𝑥=1

= 𝑒 𝑡 𝑝(1) + 𝑒 2𝑡 𝑝(2) + 𝑒 3𝑡 𝑝(3) + ⋯ … ….

1 1 1
= 𝑒𝑡 + 𝑒 2𝑡 2 + 𝑒 3𝑡 3 + ⋯ … ….
2 2 2
2
1 𝑒𝑡 𝑒𝑡
= 𝑒 [1 + ( ) + ( ) + ⋯ … . . ] 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−1 = 1 + 𝑥 + 𝑥 2 + ⋯ … ….
𝑡
2 2 2

−1
𝑒𝑡 𝑒𝑡
= [1 − ( )]
2 2
−1
𝑒𝑡 2 − 𝑒𝑡
= [ ]
2 2

𝑒𝑡 2
= [ ]
2 2 − 𝑒𝑡
𝑒𝑡
𝑀𝑋 (𝑡) =2−𝑒 𝑡

To find Mean

𝑬(𝑿) = ∑ 𝒙 𝒑(𝒙) = 𝟏𝒑(𝟏) + 𝟐𝒑(𝟐) + 𝟑𝒑(𝟑) + ⋯ … … ..


𝒙=𝟏

1 1 2 1 3
= 1 ( ) + 2 ( ) + 3 ( ) + ⋯ … … ..
2 2 2
1 1 1 2 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−2 = 1 + 2𝑥 + 3𝑥 2 + ⋯ … . .
= [1 + 2 ( ) + 3 ( ) + ⋯ … … . ] { }
2 2 2 𝑃𝑟𝑜𝑣𝑖𝑑𝑒𝑑 |𝑥| < 1

1 1 −2 1 1 −2
= [1 − ] = ( )
2 2 2 2
1 1
= (2)2 = (4)
2 2
𝐸(𝑋) = 2 …………………..(1)

To find Variance

Var(X)=E(X2)-(E(X))2
∞ ∞

𝐸(𝑋 2 ) = ∑ 𝑥 2 𝑝(𝑥) = ∑[𝑥(𝑥 + 1) − 𝑥] 𝑝(𝑥)


𝑥=1 𝑥=1

∞ ∞

= ∑ 𝑥(𝑥 + 1)𝑝(𝑥) − ∑ 𝑥𝑝(𝑥)


𝑥=1 𝑥=1

= ∑ 𝑥(𝑥 + 1)𝑝(𝑥) − 2 𝑏𝑦 (1) … … … . . (2)


𝑥=1

∑ 𝑥(𝑥 + 1)𝑝(𝑥) = 1(2)𝑝(1) + 2(3)𝑝(2) + 3(4)𝑝(3) + ⋯ … … . .


𝑥=1

1 1 2 1 3
= 1(2) ( ) + 2(3) ( ) + 3(4) ( ) + ⋯ … … ..
2 2 2

1 1 1 2
= 2 ( ) [1 + 3 ( ) + 6 ( ) + ⋯ … … . ]
2 2 2

1 −3
= (1 − ) 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−3 = 1 + 3𝑥 + 6𝑥 2 + ⋯ … ….
2

1 −3
= ( ) = 23 = 8
2
Substitute in (2), we get

𝐸(𝑋 2 ) = 8 − 2 = 6

∴ 𝑉𝑎𝑟(𝑋) = 6−(2)2 = 2
To find 𝑷(𝑿 𝒊𝒔 𝒆𝒗𝒆𝒏)

𝑃(𝑋 𝑖𝑠 𝑒𝑣𝑒𝑛) = 𝑃(𝑋 = 2,4,6, … … . . )

= 𝑃(𝑋 = 2) + 𝑃(𝑋 = 4) + 𝑃(𝑋 = 6) + ⋯ … … ….

1 2 1 4 1 6
= ( ) + ( ) + ( ) + ⋯ … … … … ..
2 2 2

1 2 1 2 1 4
= ( ) [1 + ( ) + ( ) + ⋯ … … … . ]
2 2 2

1 1 1 2
= [1 + + ( ) + ⋯ … … . ]
4 4 4

1 1 −1
= (1 − ) 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−1
4 4
= 1 + 𝑥 + 𝑥 2 + ⋯ … . . 𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑑 |𝑥| < 1

1 3 −1
= ( )
4 4
1 4 1
= ( )=
4 3 3
To find 𝑷(𝑿 ≥ 𝟓)

𝑃(𝑋 ≥ 5) = 𝑃(𝑋 = 5,6,7, … … )

= 𝑃(𝑋 = 5) + 𝑃(𝑋 = 6) + 𝑃(𝑋 = 7) + ⋯ … ..

1 1 1
= 5
+ 6 + 7 + ⋯ ….
2 2 2

1 1 1 2
= 5 [1 + + ( ) + ⋯ … . ]
2 2 2

1 1 −1
= (1 − ) 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−1
32 2
= 1 + 𝑥 + 𝑥 2 + ⋯ … . . 𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑑 |𝑥| < 1

1 1
= (2) =
32 16
To find 𝑷(𝑿 𝒊𝒔 𝒅𝒊𝒗𝒊𝒔𝒊𝒃𝒍𝒆 𝒃𝒚 𝟑)

𝑃(𝑋 𝑖𝑠 𝑑𝑖𝑣𝑖𝑠𝑖𝑏𝑙𝑒 𝑏𝑦 3) = 𝑃(𝑋 = 3,6,9, … … … )

= 𝑃(𝑋 = 3) + 𝑃(𝑋 = 6) + 𝑃(𝑋 = 9) + ⋯ …


1 1 1
= + + + ⋯ ….
23 26 29

1 1 2 1 3
= 3 + ( 3 ) + ( 3 ) + ⋯ ….
2 2 2

1 1 2 1 3
= +( ) +( ) +⋯…
8 8 8

1 1 1 2
= [1 + + ( ) + ⋯ … ]
8 8 8

1 1 −1
= (1 − ) 𝑠𝑖𝑛𝑐𝑒 (1 − 𝑥)−1 = 1 + 𝑥 + 𝑥 2 + ⋯ … . . 𝑝𝑟𝑜𝑣𝑖𝑑𝑒𝑑 |𝑥| < 1
8 8

1 7 −1 1 8 1
= ( ) = ( )=
8 8 8 7 7

2. If X represents the outcome of a fair die, find the moment generating function of X and
hence find E(X) and Var(X).

Solution:
1
The probability distribution of X is given by 𝑃(𝑋 = 𝑥) = 6 , 𝑥 = 1,2,3,4,5,6

𝑥𝑖 1 2 3 4 5 6
𝑝𝑖 1 1 1 1 1 1
6 6 6 6 6 6

To find MGF
6

𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = ∑ 𝑒 𝑡𝑥 𝑝(𝑥)


𝑥=1

= 𝑒 𝑡 𝑝(1) + 𝑒 2𝑡 𝑝(2)+𝑒 3𝑡 𝑝(3) + 𝑒 4𝑡 𝑝(4) + 𝑒 5𝑡 𝑝(5) + 𝑒 6𝑡 𝑝(6)

1 1 1 1 1 1
= 𝑒 𝑡 + 𝑒 2𝑡 + 𝑒 3𝑡 +𝑒 4𝑡 + 𝑒 5𝑡 + 𝑒 6𝑡
6 6 6 6 6 6
1 𝑡
𝑀𝑋 (𝑡) = [𝑒 + 𝑒 2𝑡 + 𝑒 3𝑡 +𝑒 4𝑡 + 𝑒 5𝑡 + 𝑒 6𝑡 ]
6
To find E(X)
6

𝐸(𝑋) = ∑ 𝑥 𝑝(𝑥)
𝑥=1
= 1𝑝(1) + 2𝑝(2)+ 3𝑝(3) + 4𝑝(4) + 5𝑝(5) + 6𝑝(6)

1 1 1 1 1 1
=1 +2 +3 4 +5 +6
6 6 6 6 6 6
1
= [1 + 2 + 3 + 4 + 5 + 6]
6
21
=
6
7
𝐸(𝑋) =
2
To find Var(X)

𝑉𝑎𝑟(𝑋) = 𝐸(𝑋 2 ) − (𝐸(𝑋))2


6

𝐸(𝑋 2 ) = ∑ 𝑥 2 𝑝(𝑥)
𝑥=1

= 1𝑝(1) + 4𝑝(2) + 9𝑝(3) + 16𝑝(4) + 25𝑝(5) + 36𝑝(6)

1 1 1 1 1 1
= 1 + 4 + 9 + 16 + 25 + 36
6 6 6 6 6 6
1
= [1 + 4 + 9 + 16 + 25 + 36]
6
91
𝐸(𝑋 2 ) =
6

91 7 2 91 49 364 − 294
∴ 𝑉𝑎𝑟(𝑋) = −( ) = − =
6 2 6 4 24
70
=
24
35
𝑉𝑎𝑟(𝑋) = .
12

𝟑
3. If a random variable X has the MGF 𝑴𝑿 (𝒕) = 𝟑−𝒕 , obtain the standard deviation of X.

Solution:
3
Given 𝑀𝑋 (𝑡) = 3−𝑡

3
= 𝑡
3 (1 − 3)
𝑡 −1
= (1 − )
3
𝑡 𝑡 2 𝑡 3
= 1 + 3 + (3) + (3) + ⋯ … …

𝑡 𝑡2 𝑡3
=1+3+ + 27 + ⋯ … − − − − − (1)
9

𝑡 𝑡2 𝑡3
W.K.T 𝑀𝑋 (𝑡) = 1 + 1! 𝜇1′ + 2! 𝜇2′ + 3! 𝜇3′ + ⋯ … .. − − − − (2)

𝑡
The coefficient of = 𝜇1′ = 𝐸(𝑋)
1!

𝑡2
The coefficient of = 𝜇2′ = 𝐸(𝑋 2 )
2!

From (1),
1 𝑡 1 𝑡 1 𝑡
𝐸(𝑋) = 𝜇1′ = 3since3 = 3 (1) = 3 (1!)

1 𝑡2 2𝑡 2 2 𝑡2 2 𝑡2
𝐸(𝑋 2 ) = 𝜇2′ = since 9 = 2∗9 = 9 ( 2 ) = 9 ( 2! )
9

∴ 𝑉𝑎𝑟(𝑋) = 𝐸(𝑋 2 ) − ( 𝐸(𝑋))2

2 1 2
= −( )
9 3
2 1 1
= − =
9 9 9

1 1
∴ 𝑆𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝐷𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 𝑜𝑓 𝑋 = √𝑉𝑎𝑟(𝑋) = √9 = 3 .

4. If the moments of a random variable X are defined by (𝑿𝒓 ) = 𝟎. 𝟔, 𝒓 = 𝟏, 𝟐, … …. .


Show that 𝑷(𝑿 = 𝟎) = 𝟎. 𝟒, 𝑷(𝑿 = 𝟏) = 𝟎. 𝟔, 𝑷(𝑿 ≥ 𝟐) = 𝟎.

Solution:
𝑡𝑟 𝑡0 𝑡𝑟
W.K.T 𝑀𝑋 (𝑡) = ∑∞ ′
𝑟=0 𝑟! 𝜇𝑟 = 𝜇 ′ + ∑∞ ′
𝑟=1 𝑟! 𝜇𝑟
0! 0

𝑡𝑟 𝑡𝑟
= 1 + ∑∞ ′ ∞ ′ 𝑟
𝑟=1 𝑟! 𝜇𝑟 = 1 + ∑𝑟=1 𝑟! (0.6) since 𝜇𝑟 = 𝐸(𝑋 ) = 0.6, 𝑟 = 1,2, … ….

𝑡1 𝑡 2 𝑡 3
= 1 + (0.6) [ + + + ⋯ … … ]
1! 2! 3!

𝑡1 𝑡 2 𝑡 3
= 1 + (0.6) [1 + + + + ⋯ … … − 1]
1! 2! 3!
𝑥1 𝑥2 𝑥3
= 1 + (0.6)[𝑒 𝑡 − 1] since 𝑒 𝑥 = 1 + + + +⋯…
1! 2! 3!

= 1 + 0.6𝑒 𝑡 − 0.6

𝑀𝑋 (𝑡) = 0.4 + 0.6𝑒 𝑡 ------------ (1)

We also know that 𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑥 ) = ∑∞ 𝑡𝑥


𝑥=0 𝑒 𝑝(𝑥)

= 𝑒 𝑡0 𝑝(0) + 𝑒 𝑡1 𝑝(1) + 𝑒 𝑡2 𝑝(2) + ⋯ … ..

= 𝑝(0) + 𝑒 𝑡 𝑝(1) + 𝑒 2𝑡 𝑝(2) + ⋯ … ..------------------ (2)

Comparing like coefficients of (1) and (2), we get

𝑝(0) = 0.4

𝑝(1) = 0.6

𝑝(2) = 0

𝑝(3) = 0, … …

That is, 𝑃(𝑋 = 0) = 0.4, 𝑃(𝑋 = 1) = 0.6, 𝑃(𝑋 ≥ 2) = 0.


𝟐
5. If a random variable X has the moment generating function 𝑴𝑿 (𝒕) = , determine
𝟐−𝒕
the variance of X.

Solution:
2
Given 𝑀𝑋 (𝑡) = 2−𝑡

2
= 𝑡
2 (1 − 2)

𝑡 −1
= (1 − )
2
𝑡 𝑡 2 𝑡 3
= 1 + 2 + (2) + (2) +………

𝑡 𝑡2 𝑡3
𝑀𝑋 (𝑡) = 1 + 2 + + +……… ------------------------ (1)
4 8

𝑡 𝑡2 𝑡3
W.K.T. 𝑀𝑋 (𝑡) = 1 + 1! 𝜇1′ + 2! 𝜇2′ + 3! 𝜇3′ + ⋯ … .. − − − − (2)

𝑡
The coefficient of = 𝜇1′ = 𝐸(𝑋)
1!
𝑡2
The coefficient of = 𝜇2′ = 𝐸(𝑋 2 )
2!

From (1),
1 𝑡 1 𝑡 1 𝑡
𝐸(𝑋) = 𝜇1′ = 2since2 = 2 (1) = 2 (1!)

1 𝑡2 𝑡2 1 𝑡2 1 𝑡2
𝐸(𝑋 2 ) = 𝜇2′ = 2since 4 = 2∗2 = 2 ( 2 ) = 2 ( 2! )

∴ 𝑉𝑎𝑟(𝑋) = 𝐸(𝑋 2 ) − ( 𝐸(𝑋))2

1 1 2
= −( )
2 2
1 1 1
= − =
2 4 4
6. Find the moment generating function of the random variable X whose moments are
𝝁𝒓 = (𝒓 + 𝟏)! 𝟐𝒓 .

Solution:
𝑡𝑟 𝑡𝑟
The moment generating function is given by 𝑀𝑋 (𝑡) = ∑∞ ∞
𝑟=0 𝑟! 𝜇𝑟 = ∑𝑟=0 𝑟! (𝑟 + 1)! 2
𝑟

= ∑ 𝑡 𝑟 (𝑟 + 1)2𝑟
𝑟=0

= ∑(2𝑡)𝑟 (𝑟 + 1)
𝑟=0

= (2𝑡)0 1 + (2𝑡)1 2 + (2𝑡)2 (3) + (2𝑡)3 (4) + ⋯ … … …

= 1 + 2(2𝑡) + 3(2𝑡)2 + 4(2𝑡)3 + ⋯ … … …

= (1 − 2𝑡)−2

1
𝑀𝑋 (𝑡) =
(1 − 2𝑡)2

7. Find the moment generating function of the random variable X having the pdf 𝒇(𝒙) =
𝒙, 𝟎 ≤ 𝒙 < 1
{𝟐 − 𝒙, 𝟏 ≤ 𝒙 < 2
𝟎, 𝒐𝒕𝒉𝒆𝒓𝒘𝒊𝒔𝒆

Solution:
To find the moment generating function 𝑀𝑋 (𝑡)

𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = ∫ 𝑒 𝑡𝑥 𝑓(𝑥)𝑑𝑥
−∞

1 2
= ∫ 𝑒 𝑡𝑥 𝑓(𝑥)𝑑𝑥 + ∫ 𝑒 𝑡𝑥 𝑓(𝑥)𝑑𝑥
0 1

1 2
= ∫ 𝑒 𝑡𝑥 𝑥 𝑑𝑥 + ∫ 𝑒 𝑡𝑥 (2 − 𝑥)𝑑𝑥
0 1

1 2
𝑒 𝑡𝑥 𝑒 𝑡𝑥 𝑒 𝑡𝑥 𝑒 𝑡𝑥
= [𝑥 − 1 2 ] + [(2 − 𝑥) − (−1) 2 ]
𝑡 𝑡 0 𝑡 𝑡 1

𝑒𝑡 𝑒𝑡 𝑒0 𝑒 2𝑡 𝑒𝑡 𝑒𝑡
= ((1 − 2 ) − (0 − 2 )) + ((0 + 2 ) − (1 + 2 ))
𝑡 𝑡 𝑡 𝑡 𝑡 𝑡

𝑒 𝑡 𝑒 𝑡 1 𝑒 2𝑡 𝑒 𝑡 𝑒 𝑡
= − + + − − 2
𝑡 𝑡2 𝑡2 𝑡2 𝑡 𝑡
1
= (1 − 2𝑒 𝑡 + 𝑒 2𝑡 )
𝑡2
1
= 2
(1 − 𝑒 𝑡 )2
𝑡

𝟐𝒆−𝟐𝒙 , 𝒙 ≥ 𝟎
8. A r.v. X has the pdf given by (𝒙) = { , find (i) the moment generating function
𝟎, 𝒙 < 0
of X and (ii) the first four moments about origin.

Solution:

(i) To find the moment generating function 𝑀𝑋 (𝑡)



𝑀𝑋 (𝑡) = 𝐸(𝑒 𝑡𝑋 ) = ∫ 𝑒 𝑡𝑥 𝑓(𝑥)𝑑𝑥
−∞


= ∫ 𝑒 𝑡𝑥 2𝑒 −2𝑥 𝑑𝑥
0


= 2 ∫ 𝑒 −(2−𝑡)𝑥 𝑑𝑥
0


𝑒 −(2−𝑡)𝑥
= 2[ ]
−(2 − 𝑡) 0

𝑒 −∞ − 𝑒 0
= 2( )
−(2 − 𝑡)
0−1
= 2[ ]
−(2 − 𝑡)

2
∴ 𝑀𝑋 (𝑡) =
2−𝑡

(ii) To find the first four moments about origin 𝜇1′ , 𝜇2′ , 𝜇3′ 𝑎𝑛𝑑 𝜇4′

2 2
𝑀𝑋 (𝑡) = =
2 − 𝑡 2 (1 − 𝑡 )
2
𝑡 −1
= (1 − )
2

𝑡 𝑡 2 𝑡 3
= 1+ + ( ) + ( ) + ⋯……
2 2 2
𝑡 𝑡2 𝑡3 𝑡4
𝑀𝑋 (𝑡) = 1 + 2 + + + 16 + ⋯ … …. ------------ (1)
4 8

W.K.T.
𝑡𝑟 𝑡 𝑡2 𝑡3 𝑡4
𝑀𝑋 (𝑡) = ∑∞ ′ ′ ′ ′ ′
𝑟=0 𝑟! 𝜇𝑟 = 1 + 1! 𝜇1 + 2! 𝜇2 + 3! 𝜇3 + 4! 𝜇4 + ⋯ … … .. ---------- (2)

Comparing (1) and (2), we get

𝑡 ′ 𝑡 1
𝜇1 = ⇒ 𝜇1′ =
1! 2 2
𝑡2 ′ 𝑡2 1
𝜇2 = ⇒ 𝜇2′ =
2! 4 2
𝑡3 ′ 𝑡3 6 3
𝜇3 = ⇒ 𝜇3′ = =
3! 8 8 4
𝑡4 ′ 𝑡4 24 3
𝜇4 = ⇒ 𝜇4′ = =
4! 16 16 2

**************************

You might also like