RANDOM VARIABLES

STATS 153

Uploading materials from this course to websites that sell such content to students is prohibited by
integrity policies, and may also put you at risk for violating copyright policies

Jan 2021
 UNIT 3: OUTLINE

1. Introduction to Random Variables

2. Discrete Random Variables

3. Mean and Variance of Discrete R.V.

4. Continuous Random Variables

5. Mean and Variance of Continuous R.V.

6. Some distributions
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
1
 UNIT OBJECTIVES:
After completing this unit, you should be able to:

• Identify random variables (Discrete and Continuous)

• Explain probability distributions (Discrete and
Continuous)
• Estimate probabilities using probability distribution
(Discrete and Continuous)
• Calculate the mean, variance and standard deviation
(Discrete and Continuous)
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
2
 INTRODUCTION TO RANDOM VARIABLES
• A random variable is the description of the outcome of a
statistical experiment.

• A random variable that may assume a finite number of

values or an infinite sequence of values is said to be discrete,
one that may assume any value in an interval on the real
number line is said to be continuous.

• We denote random variables using capital letters such as X,

Y or Z.
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
3
 RULES FOR DISCRETE PROBABILITY
DISTRIBUTION
• The sum of the probabilities of all the possible values of a
discrete random variable must equals to 1.
i.e. ∑ 𝑷 𝑿 = 𝟏
• The probability of each variable 𝑋 lies between 0 and 1.
i.e. 𝟎 ≤ 𝑷 𝒙 ≤ 𝟏
• Calculating the probabilities of a discrete random variables
∑ 𝑷 𝑿 = 𝟏 Or
∑ 𝑷𝒊 = 𝟏, for 𝒊 = 𝟏, 𝟐, … 𝒏
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
4
 Example 3.1
• The discrete random variable 𝑋 has the given probability
distribution:
𝑥 1 2 3 4 5

𝑃(𝑋 = 𝑥) 0.2 0.25 0.4 𝑎 0.05

a) Find 𝑃 1 ≤ 𝑋 ≤ 3
b) Find 𝑃 𝑋 > 2
c) Find 𝑃 2 < 𝑋 < 5

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
5
 Solution 3.1
• ∑" 𝑃 𝑋 = 𝑥 = 1
=> 0.2 + 0.25 + 0.4 + 𝑎 + 0.05 = 1
𝑎 + 0.9 = 1
𝑎 = 0.1
Now:
𝑥 1 2 3 4 5

𝑃(𝑋 = 𝑥) 0.2 0.25 0.4 0.1 0.05

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
6
 Solution 3.1 cont’d.
a) 𝑃 1 ≤ 𝑋 ≤ 3 = 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3

= 0.2 + 0.25 + 0.4 = 0.85

b) 𝑃 𝑋 > 2 =𝑃 𝑋 =3 +𝑃 𝑋 =4 +𝑃 𝑋 =5

= 0.4 + 0.1 + 0.05 = 0.55

c) 𝑃 2 < 𝑋 < 5 = 𝑃 𝑋 = 3 + 𝑃 𝑋 = 4

= 0.4 + 0.1 = 0.5

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
7
 Example 3.2
• The probability density function of a discrete random
variable 𝑋 is given by 𝑃 𝑋 = 𝑥 = 𝑘𝑥 for 𝑥 = 12, 13, 14.
Write out the probability distribution and find the value of k.

Solution 3.2
To find k,
𝑥 12 13 14
C𝑃 𝑋 = 𝑥 = 1
𝑃(𝑋 = 𝑥) 12𝑘 13𝑘 14𝑘
12𝑘 + 13𝑘 + 14𝑘 = 1
𝑘 = 1/39
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
8
 MEAN AND VARIABILITY OF DISCRETE R.V.
• Mean 𝐸 𝑋 = 𝜇 = ∑#$$ % 𝑥𝑃 𝑋 = 𝑥
OR
𝜇 = C 𝑥" 𝑝" , 𝑖 = 0,1,2, … 𝑛

• Steps:
• Multiply each possible value of 𝑥 by its probability
• Add the resulting product

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
9
 Example 3.3
• The probability distribution of the random variable X is shown
in the table:
𝑥 0 1 2 3 4

𝑃(𝑋 = 𝑥) 1/6 1/12 1/4 1/3 1/6

• Find 𝐸 𝑋

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
10
 Solution 3.3
𝐸 𝑋 = C 𝑥𝑃 𝑋 = 𝑥
#$$ %
& & & & &
=> 0× ' + 1× &( + 2× ) + 3× * + 4× ' = 2.25

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
11
 Example 3.4
• The random variable X has the probability density function
p.d.f : P X=x for x=5, 6,7,8,9 as defined in the table.

𝑥 5 6 7 8 9

𝑃(𝑋 = 𝑥) 3/11 2/11 1/11 2/11 3/11

• Find 𝜇

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
12
 Solution 3.4
𝐸 𝑋 = C 𝑥𝑃 𝑋 = 𝑥
#$$ %
* ( & ( *
=> 𝜇 = 5× && + 6× && + 7× && + 8× && + 9× && = 7

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
13
 VARIABILITY OF A DISCRETE RANDOM VARIABLE
• Variance or standard deviation of a random variable X
measures whether a particular value of that random variable
is unusual.
• As mean ( 𝜇) of random variable X is a measures center or
central tendency, the variance ( 𝜎 ( ) and standard deviation
(𝜎) measure the spread or the dispersion.
• The variance of a discrete random variable X is given by
• 𝜎 ( = 𝐸 𝑋 ( − 𝜇(
( ( (
• 𝜎 =𝐸 𝑋 − 𝐸 𝑋

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
14
 VARIABILITY OF A DISCRETE RANDOM VARIABLE
( ( (
•𝜎 =𝐸 𝑋 − 𝐸 𝑋
• 𝐸 𝑋 ( = ∑#$$ % 𝑥 ( 𝑃 𝑋 = 𝑥
• 𝐸 𝑋 = ∑#$$ % 𝑥𝑃 𝑋 = 𝑥
• Standard deviation (𝜎) = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝜎 (
Definition formulas Computation formulas

𝜎 2 = $(𝑋 − 𝜇)2 𝑃(𝑋) 𝜎 2 = $+𝑋 2 𝑃(𝑋), − 𝜇2

𝜎 = -$(𝑋 − 𝜇)2 𝑃(𝑋) 𝜎 = -$+𝑋 2 𝑃(𝑋), − 𝜇2

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
15
 Example 3.5
• The random variable X has a probability distribution as shown
in the table:
𝑥 1 2 3 4 5

𝑃(𝑋 = 𝑥) 0.1 0.3 0.2 0.3 0.1

a) Find 𝜇 = 𝐸 𝑋
b) Find 𝐸(𝑋 ( )
c) Find the variance
d) Find the standard deviation
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
16
 Solution 3.5
(a) 𝜇 = 𝐸 𝑋 = ∑#$$ % 𝑥𝑃 𝑋 = 𝑥
= 1×0.1 + 2×0.3 + 3×0.2 + 4×0.3 + 5×0.1 = 3
(b) 𝐸 𝑋 ( = ∑ 𝑥 ( 𝑃(𝑋 = 𝑥)
= 1( ×0.1 + 2( ×0.3 + 3( ×0.2 + 4( ×0.3 + 5( ×0.1
= 10.4
(c) Var(X)= 𝐸 𝑋 ( − 𝜇(
= 10.4 − 9 = 1.4
(d) 𝜎 = 1.4 = 1.18

17
 Example 3.6
• The discrete random variable X has a probability density
function (pdf):
𝑃 𝑋 = 0 = 0.05, 𝑃 𝑋 = 1 = 0.45, 𝑃 𝑋 = 2 = 0.5
(a) Find 𝜇 = 𝐸 𝑋
(b) Find 𝐸 𝑋 (
(c) Var (𝑋)
(d) 𝜎(𝑋)

18
 Solution 3.6
𝑥 0 1 2

𝑃(𝑋 = 𝑥) 0.05 0.45 0.5

(a) 𝜇 = ∑ 𝑥𝑃(𝑋 = 𝑥)
= 0×0.05 + 1×0.45 + 2×0.5 = 1.45
(b) 𝐸 𝑋 ( = 0( ×0.05 + 1( ×0.45 + 2( ×0.5 = 2.45
(c) Var (𝑋 ( ) = 𝐸 𝑋 ( − 𝜇(
(
= 2.45 − 1.45 = 0.35
(d) 𝜎 = 0.35 = 0.59
19
 Results Relating to Expectation and Variance
• Given that a and b are constant
1. 𝐸 𝑎 = 𝑎
2. 𝐸 𝑎𝑋 = 𝑎𝐸(𝑋)
3. 𝐸 𝑎𝑋 + 𝑏 = 𝑎𝐸 𝑋 + 𝑏
4. V𝑎𝑟 𝑎 = 0
5. V𝑎𝑟 𝑎𝑋 = 𝑎( 𝑉𝑎𝑟(𝑋)
6. V𝑎𝑟 𝑎𝑋 + 𝑏 = 𝑎( 𝑉𝑎𝑟(𝑋)
20
 Example 3.7
• The random variable X taking integer values only has
probability density function
𝑃 𝑋 = 𝑥 = 𝑘𝑥, 𝑥 = 1, 2, 3, 4, 5
𝑃 𝑋 = 𝑥 = 𝑘 10 − 𝑥 , 𝑥 = 6, 7, 8, 9
(a) Find the value of the constant 𝑘
(b) Find 𝐸 𝑋
(c) Find Var(X)
(d) Find 𝐸(2𝑋 − 3)
(e) Find Var(2𝑋 − 3)
21
 Solution 3.7
To find k, 𝑥 1 2 3 4 5 6 7 8 9

𝑃(𝑋 = 𝑥) 𝑘 2𝑘 3𝑘 4𝑘 5𝑘 4𝑘 3𝑘 2𝑘 𝑘
(a) ∑ 𝑃 𝑋 = 𝑥 = 1
𝑘 + 2𝑘 + 3𝑘 + 4𝑘 + 5𝑘 + 4𝑘 + 3𝑘 + 2𝑘 + 𝑘 = 1
25𝑘 = 1
=> 𝑘 = 1/25

𝑥 1 2 3 4 5 6 7 8 9

𝑃(𝑋 = 𝑥) 1/25 2/25 3/25 4/25 5/25 4/25 3/25 2/25 1/25

22
 Solution 3.7 cont’d.
! " $ % # % $
(b) 𝐸 𝑋 = 1× "# + 2× "# + 3× "# + 4× "# + 5× "# + 6× "# + 7× "#
" !
+8× + 9×
"# "#
=5
(c) Var (X) = 𝐸 𝑋 " − (𝐸(𝑋)" )
" " ! " " " $ " % " # " %
𝐸 𝑋 =1 × "# +
2 +3 × "# × "# +4 × "# +5 × "# +6 × "#
"
3 "
12 "
+7 × + 8 × + 9 ×
25 25 25
= 29
:. Var (X)= 29 − 5"
=4

23
 Solution 3.7 cont’d.
(d) 𝐸 2𝑋 − 3 = 2𝐸 𝑋 − 3
=2 5 −3=7
(e) Var 2𝑋 − 3 = 2( 𝑉𝑎𝑟 𝑋
= 4 4 = 16

24
 Example 3.8
• The discrete random variable X has probability density
function P X=x =k for x=1, 2, 3, 4, 5, 6
(a) Find 𝐸 𝑋
(b) Find 𝐸 𝑋 (
(c) Find 𝐸 3𝑋 + 4
(d) Find Var(X)
(e) Find V𝑎𝑟 2𝑋 + 3

25
 Solution 3.8
To find k, 𝑥 1 2 3 4 5 6

∑#$$ % 𝑃 𝑋 = 𝑥 = 1 𝑃(𝑋 = 𝑥) k k k k k k

𝑘+𝑘+𝑘+𝑘+𝑘+𝑘 =1
&
𝑘=
'
Now:

𝑥 1 2 3 4 5 6

𝑃(𝑋 = 𝑥) 1/6 1/6 1/6 1/6 1/6 1/6

26
 Solution 3.8 cont’d
(a) 𝐸 𝑋 = ∑!"" # 𝑥𝑃 𝑋 = 𝑥
$ $ $ $ $ $
1× + 2× + 3× + 4× + 5× + 6× = 3.5
% % % % % %

(b) 𝐸 𝑋 & = ∑!"" # 𝑥 & 𝑃 𝑋 = 𝑥

$ $ $ $ $ $ '$
= 1& × + 2& × + 3& × + 4& × + 5& × + 6& × =
% % % % % % %

(c) 𝐸 3𝑋 + 4 = 3𝐸 𝑋 + 4
= 3 3.5 + 4 = 14.5
&
(d) 𝑉𝑎𝑟 𝑋 = 𝐸 𝑋 & − 𝐸 𝑋
'$ &$ &
= −
% %
= 2.92
(e) 𝑉𝑎𝑟 2𝑋 + 3 = 4𝑣𝑎𝑟 𝑋
= 4 2.92 = 11.68
27
 INDEPENDENT RANDOM VARIABLES
• Given two random variables X and Y and the constants a
and b;
(1) 𝐸 𝑎𝑋 + 𝑏𝑌 = 𝑎𝐸 𝑋 + 𝑏𝐸 𝑌
(2) 𝐸 𝑎𝑋 − 𝑏𝑌 = 𝑎𝐸 𝑋 − 𝑏𝐸 𝑌
(3) 𝐸 𝑎𝑋 + 𝑏 = 𝑎𝐸 𝑋 + 𝑏
(4) 𝐸 𝑎𝑋 − 𝑏 = 𝑎𝐸 𝑋 + 𝑏
(5) 𝐸 𝑏 = 𝑏
(6) 𝐸 𝑋& + 𝑋( + ⋯ + 𝑋A = 𝑛𝐸(𝑋)
28
 INDEPENDENT RANDOM VARIABLES cont’d.
• If X and Y are independent, then
(7) 𝑉𝑎𝑟 𝑎𝑋 + 𝑏𝑌 = 𝑎( 𝑉𝑎𝑟 𝑋 + 𝑏 ( 𝑉𝑎𝑟 𝑌
(8) 𝑉𝑎𝑟 𝑎𝑋 − 𝑏𝑌 = 𝑎( 𝑉𝑎𝑟 𝑋 + 𝑏 ( 𝑉𝑎𝑟 𝑌
(9) 𝑉𝑎𝑟 𝑎𝑋 + 𝑏 = 𝑎( 𝑉𝑎𝑟 𝑋
(10) 𝑉𝑎𝑟 𝑎𝑋 − 𝑏 = 𝑎( 𝑉𝑎𝑟 𝑋
(11) 𝑉𝑎𝑟 𝑎 = 0
(12) 𝑉𝑎𝑟 𝑋& + 𝑋( + ⋯ + 𝑋A = 𝑛𝑉𝑎𝑟 𝑋

29
 Example 3.11
Independent random variables X and Y are such that
𝐸 𝑋 = 4, 𝐸 𝑌 = 5, 𝑉𝑎𝑟 𝑋 = 1 𝑎𝑛𝑑 𝑉𝑎𝑟 𝑌 = 2

(a) Find 𝐸 4𝑋 + 2𝑌

(b) Find 𝐸 5𝑋 − 𝑌

(c) 𝑉𝑎𝑟 3𝑋 + 2𝑌

(d) 𝑉𝑎𝑟 5𝑋 − 3𝑌

30
 Solution 3.11
• 𝐸 𝑋 = 4, 𝐸 𝑌 = 5, 𝑉𝑎𝑟 𝑋 = 1 𝑎𝑛𝑑 𝑉𝑎𝑟 𝑌 = 2

(a) 𝐸 4𝑋 + 2𝑌 = 4𝐸 𝑋 + 2𝐸 𝑌 = 4×4 + 2×5 = 16 + 10 = 26

(b) 𝐸 5𝑋 − 𝑌 = 5𝐸 𝑋 − 𝐸 𝑌 = 5×4 − 5 = 20 − 5 = 15

(c) 𝑉𝑎𝑟 3𝑋 + 2𝑌 = 3( 𝑉𝑎𝑟 𝑋 + 2( 𝑉𝑎𝑟 𝑌 = 9×1 + 4×2 = 17

(d) 𝑉𝑎𝑟 5𝑋 − 3𝑌 = 5( 𝑉𝑎𝑟 𝑋 + −3 ( 𝑉𝑎𝑟 𝑌 = 25×1 + 9×2 = 43

31
 Example 3.12
• Independent random variables X and Y are such that
𝐸 𝑋 ( = 14, 𝐸 𝑌 ( = 20, 𝑉𝑎𝑟 𝑋 = 10 𝑎𝑛𝑑 𝑉𝑎𝑟 𝑌 = 11

(a) Find 𝐸 3𝑋 − 2𝑌

(b) Find 𝑉𝑎𝑟 5𝑋 − 2𝑌

32
 Solution 3.12
First solve for 𝑬(𝑿) and 𝑬(𝒀).
𝑉𝑎𝑟 𝑋 = 𝐸 𝑋 " − 𝐸 " 𝑋 and 𝑉𝑎𝑟 𝑌 = 𝐸 𝑌 " − 𝐸 " (𝑌)
10 = 14 − 𝐸 " (𝑋) 11 = 20 − 𝐸 " (𝑌)
𝐸 " 𝑋 = 14 − 10 = 4 𝐸 " 𝑌 = 20 − 11 = 9
=> 𝐸 𝑋 = ±2 => 𝐸 𝑌 = ±3
• Here both answers are valid and as such, a solution must be
chosen based on the question as to whether 𝑬 𝑿 > 𝟎 and 𝑬 𝒀 >
𝟎 or otherwise.
• We choose 𝐸 𝑋 > 0 and 𝐸 𝑌 > 0. (NB: This is by choice!)
(a) 𝐸 3𝑋 − 2𝑌 = 3𝐸 𝑋 − 2𝐸 𝑌 = 3×2 − 2×3 = 0
(b) 𝑉𝑎𝑟 5𝑋 − 2𝑌 = 25𝑉𝑎𝑟 𝑋 + 4𝑉𝑎𝑟 𝑌 = 25×2 + 4×3 = 62

33
 CONTINUOUS
RANDOM VARIABLES

34
 CONTINUOUS RANDOM VARIABLES
• Examples of continuous random variables:
• The mass, grams, of bag of sugar packaged by a particular
machine.
• The time taken, in minutes, to perform a task.
• The height, in centimetres, of a ten-year old boy.
• The lifetime, in hours, of a 100-watt light bulb.

35
 PROBABILITY DENSITY FUNCTION OF CONTINUOUS R.V.

• Continuous random variable 𝑋, with p.d.f, 𝑓(𝑥) is valid over

the range, 𝑎 ≤ 𝑥 ≤ 𝑏 if

B
• ∫# 𝑓(𝑥) 𝑑𝑥 =1

• 𝑓𝑜𝑟 𝑎 ≤ 𝑥& < 𝑥( ≤ 𝑏

%"
• 𝑃 𝑥& ≤ 𝑋 ≤ 𝑥( = ∫% 𝑓(𝑥) 𝑑𝑥
!

36
 Example 3.13
• A continuous random variable had p.d.f 𝑓 𝑥 = 𝑘𝑥 ( 𝑓𝑜𝑟 0 ≤
𝑥 ≤ 4.
a) Find the value of the constant 𝑘.
b) Find 𝑃(1 ≤ 𝑋 ≤ 3).

37
 Solution 3.13
%
a) ∫& 𝑓(𝑥) 𝑑𝑥 =1
%
B 𝑘𝑥 " 𝑑𝑥 = 1
&
$ %
𝑘𝑥
=1
3 &
64
𝑘=1
3
3
𝑘=
64
$' !
∴𝑓 𝑥 = , 𝑓𝑜𝑟 0 ≤ 𝑥 ≤ 4.
(%
38
 Solution 3.13 cont’d.
* * (
b) 𝑃 1 ≤ 𝑋 ≤ 3 = ∫& ') 𝑥 𝑑𝑥
* *
3 𝑥
=
64 3 &
3 3* 1*
= −
64 3 3
3 1
= 9−
64 3
= 0.41

39
 Example 3.14
• The continuous random variable 𝑋 has pdf 𝑓(𝑥) where
𝑘 𝑥 + 2 ( −2 ≤ 𝑥 < 0
𝑓 𝑥 =] 4𝑘 0≤𝑥≤2
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
a) Find the value of the constant 𝑘.
b) Find 𝑃(−1 ≤ 𝑋 ≤ 1).
c) Find 𝑃(𝑋 > 1).

40
 Solution 3.14
a) To find 𝑘, ∫)** ' 𝑓 𝑥 𝑑𝑥 = 1
& " "
• ∫+" 𝑘 𝑥 + 2 𝑑𝑥 + ∫& 4𝑘 𝑑𝑥 = 1
, $ & "
• $
𝑥 + 2 +" + 𝑘 4𝑥 & =1
,
• 0 + 2 $ − −2 + 2 $ + 4𝑘 2−0 =1
$
,
• $
8 + 8𝑘 = 1
-
• 𝑘 +8 =1
$
$"
• $
𝑘 = 1
$
• 𝑘=
$"
41
 Solution 3.14 cont’d.
D * ( & *
b) 𝑃 −1 ≤ 𝑋 ≤ 1 = ∫C& *( 𝑥 + 2 𝑑𝑥 + ∫D *( ×4 𝑑𝑥
D * ( &*
•= ∫C& *( 𝑥+2 𝑑𝑥 + ∫D E 𝑑𝑥
D &
* %F( # *
•= × + 𝑥
*( * C& E D
& * * *
• = *( 0 + 2 − −1 + 2 +E 1−0
& *
• = *( 8 − 1 + E
G *
•= +
*( E
• = 0.59
42
 Solution 3.14 cont’d.
( *
c) 𝑃 𝑋 > 1 = ∫& *( ×4 𝑑𝑥
* (
•=E 𝑥 &
*
•= 2−1
E
*
•=
E
• = 0.38

43
 EXPECTATION OF X, 𝑬(𝑿)
• For a continuous random variable with pdf 𝑓 𝑥 .
𝐸 𝑋 =b 𝑥𝑓(𝑥) 𝑑𝑥
#$$ %

• Example 3.15
X is a continuous random variable with pdf 𝑓 𝑥 = 𝑘𝑥 ( 𝑓𝑜𝑟
0 ≤ 𝑥 ≤ 5.
Find 𝐸(𝑋).

44
 Solution 3.15
• To find 𝑘, • => 𝑥𝑓 𝑥 = 𝑥 1
&
𝑥# =
&
𝑥&
" '#" '#"
• ∫! 𝑘𝑥 # 𝑑𝑥 = 1 " &
• 𝐸 𝑋 = ∫! '#" 𝑥 & 𝑑𝑥
" "
$% ! 3 𝑥*
• =1
& ! =
'#" 125 4 !
• 𝑘−0 =1 3 5*
&
= −0
• 𝑘=
& 125 4
'#" 3 625
& =
• ∴𝑓 𝑥 = 𝑥# 125 4
'#" 15
• 𝐸 𝑋 = ∫()) % 𝑥𝑓(𝑥) 𝑑𝑥 =
4
= 3.75

45
 Example 3.16
• A random variable X has a pdf 𝑓(𝑥) given by
𝑓 𝑥 = 𝑐𝑥 5 − 𝑥 , 0 ≤ 𝑥 ≤ 5.
Find the mean of X.

Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
46
 Solution 3.16
1. 𝐸 𝑋 = ∫()) % 𝑥𝑓(𝑥) 𝑑𝑥 2. ∫()) % 𝑓(𝑥) 𝑑𝑥 = 1
• ∫()) % 𝑓 𝑥 𝑑𝑥 = 1
"
• ∫! 𝑐𝑥 5 − 𝑥 𝑑𝑥 = 1
"
• ∫! 𝑐 5𝑥 − 𝑥 # 𝑑𝑥 = 1
"
"% " %!
• 𝑐 # − & =1
!
'#" '#"
• 𝑐 − =1
# &
'#"
• 𝑐 =1
+
+
• 𝑐=
'#"

47
 Solution 3.16 cont’d.
• 𝑚𝑒𝑎𝑛 = 𝐸 𝑋 = ∫!"" # 𝑥𝑓(𝑥) 𝑑𝑥
% %
• => 𝑥𝑓 𝑥 = 𝑥 Q 𝑥 5−𝑥 = 𝑥& 5−𝑥
$&( $&(
% ( &
• 𝐸 𝑋 = ∫ 𝑥 5 − 𝑥 𝑑𝑥
$&% ) (
6
= R 5𝑥 & − 𝑥 * 𝑑𝑥
126 )
(
6 5𝑥 * 𝑥 +
= −
125 3 4 )
6 625 625
= − −0
125 3 4
6 625
= Q
125 12
5
=6Q
12
= 2.5

48
 VARIANCE OF X, 𝑽𝒂𝒓(𝑿)
• If 𝑋 is a continuous random variable with pdf 𝑓(𝑥) then

• 𝑉𝑎𝑟 𝑋 = ∫#$$% 𝑥 ( 𝑓 𝑥 𝑑𝑥 − 𝜇(

where

• 𝜇 = 𝐸 𝑋 = ∫#$$ % 𝑥𝑓(𝑥) 𝑑𝑥

• The standard deviation of X is often written as 𝜎.

•𝜎= 𝑉𝑎𝑟(𝑋)
Uploading materials from this course to websites that sell such content to students is prohibited by integrity policies, and may also put you at risk for violating copyright policies
49
 Example 3.17
!
• The continuous random variable X has pdf 𝑓 𝑥 = -
𝑥, 0 ≤ 𝑥 ≤ 4.

a) Find 𝐸(𝑋).

b) Find 𝐸(𝑋 " ).

c) Find 𝑉𝑎𝑟(𝑋).

d) Find 𝜎. , the standard deviation of X.

e) Find 𝑉𝑎𝑟(3𝑋 + 2).

50
 Solution 3.17
a) 𝐸 𝑋 = ∫#$$% 𝑥𝑓 𝑥 𝑑𝑥 b) 𝐸 𝑋 ( = ∫#$$% 𝑥 ( 𝑓 𝑥 𝑑𝑥
) )
1 ( 1 *
= b 𝑥 𝑑𝑥 = b 𝑥 𝑑𝑥
D 8 ) D 8 )
1 𝑥* 1 𝑥)
= =
8 3 D 8 4 D
1 4* 1 4)
= −0 = −0
8 3 8 4
= 2.7 =8

51
 Solution 3.17 cont’d.
c) 𝑉𝑎𝑟 𝑋 = 𝐸 𝑋 ( − 𝐸 𝑋 (
= 8 − 2.7( = 0.89

d) 𝜎T = 𝑉𝑎𝑟 𝑋 = 0.89 = 0.94

e) 𝑉𝑎𝑟 3𝑋 + 2 = 𝑉𝑎𝑟 3𝑋 + 𝑉𝑎𝑟 2 = 3( 𝑉𝑎𝑟 𝑋 + 0 = 9×𝑉𝑎𝑟 𝑋

= 9×0.89
= 8.0

52
 Example 3.18
• An experiment of temporary roundabout is installed at the
crossroads, the time, X minutes, which vehicles have to wait
before entering the roundabout has probability density
function
0.8 − 0.32𝑥 0 ≤ 𝑥 ≤ 2.5
𝑓 𝑥 =e
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
Find the mean and the standard deviation of X.

53
 Solution 3.18
• 𝐸 𝑋 = ∫#$$% 𝑥𝑓 𝑥 𝑑𝑥
(.U
=b 0.8𝑥 − 0.32𝑥 ( 𝑑𝑥
D
( * (.U
0.8𝑥 0.32𝑥
= −
2 3 D
(
0.8 2.5 0.32 2.5*
= − −0
2 3
= 0.833 𝑚𝑖𝑛𝑢𝑡𝑒𝑠
= 50 𝑠𝑒𝑐𝑜𝑛𝑑𝑠
∴ 𝑇ℎ𝑒 𝑚𝑒𝑎𝑛 𝑡𝑖𝑚𝑒 𝑖𝑠 50 𝑠𝑒𝑐𝑜𝑛𝑑𝑠

54
 Solution 3.18 cont’d.
• 𝐸 𝑋 " = ∫#$$% 𝑥 " 𝑓 𝑥 𝑑𝑥
".(
= ( 0.8𝑥 " − 0.32𝑥 ) 𝑑𝑥
& ".(
0.8𝑥 ) 0.32𝑥 *
= −
3 4 &
)
0.8 2.5 0.32 2.5*
= − −0
4 4
= 1.041
• 𝑉𝑎𝑟 𝑋 = 𝐸 𝑋 " − 𝐸 " 𝑋
= 1.041 − 0.833 "
= 0.347
• 𝑆𝐷 𝑋 = 𝑉𝑎𝑟 𝑋 = 0.347 = 0.589
• The standard deviation is 35 seconds.
55
 Some distributions

56
 A BINOMIAL MODEL
• The probability, 𝑝, of a successful outcome is the same for
each trial.
• The discrete random variable, 𝑋, is the number of successful
outcomes in 𝒏 trials.
• If these conditions are satisfied, 𝑋 is said to follow a binomial
distribution denoted as:
𝑋~𝐵(𝑛, 𝑝)

57
 DISTRIBUTION FOR A BINOMIAL MODEL
• The distribution of the binomial model is:
𝑃 𝑋 = 𝑥 = 𝑛𝐶% 𝑝 % 1 − 𝑝 AC%
for 𝑥 = 0, 1, 2, 3, … , 𝑛

• NB: 𝒑 is the probability of success

𝒏 is the number of trials
𝒒 = 𝟏 − 𝒑 is the probability of failure
𝒏
𝒏𝑪𝒙 is same as 𝒙
i.e. 𝒏 Combination 𝒙
𝒏 and 𝒑 are the parameters for binomial probability.
58
 Example 4.1
• Given that the random variable 𝑋 is binomially distributed
with 𝑛 = 10 and 𝑝 = 0.2. That is 𝑋~𝐵 10, 0.2 .
a) Find 𝑃(𝑋 = 0).
b) Find 𝑃(𝑋 ≤ 3).
c) Find 𝑃(𝑋 > 3).
d) Find 𝑃(2 < 𝑋 ≤ 5).
e) Find 𝑃(𝑋 = 10).

59
 Solution 4.1
𝑿~𝑩(𝟏𝟎, 𝟎. 𝟐) where 𝒏 = 𝟏𝟎 and 𝒑 = 𝟎. 𝟐 => 𝒒 = 𝟏 − 𝒑 = 𝟏 − 𝟎. 𝟐 = 𝟎. 𝟖
a) 𝑃 𝑋 = 0 = 10𝐶0 0.2& 1 − 0.2 +&,& = 1×1×0.8+& = 0.1074
b) 𝑃 𝑋 ≤ 3 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3
= 10𝐶0 0.2& 1 − 0.2 +&,&
+ 10𝐶1 0.2+ 1 − 0.2 +&,+
+ 10𝐶2 0.2" 1 − 0.2 +&,"

+ 10𝐶3 0.2) 1 − 0.2 +&,)

= 0.8791
OR compactly as:
𝑃 𝑋 ≤3 =𝑃 𝑋 =0 +𝑃 𝑋 =1 +𝑃 𝑋 =2 +𝑃 𝑋 =3
)

= N 10𝐶𝑥 0.2% 1 − 0.2 +&,%

%-&
= 0.8791

60
 Solution 4.1 cont’d.
c) 𝑃 𝑋 > 3 = 1 − 𝑃 𝑋 ≤ 3 = 1 − 0.8791 = 0.1209
OR one can compute for 𝑃 𝑋 ≥ 4
&D

= C 10𝐶𝑥 0.2% 1 − 0.2 &DC%

= 0.1209
%X)

d) 𝑃 2 < 𝑋 ≤ 5 = 𝑃 3 ≤ 𝑋 ≤ 5 = 𝑃 𝑋 = 3 + 𝑃 𝑋 = 4 + 𝑃 𝑋 = 5
= 10𝐶0 0.2* 1 − 0.2 &DC*
+ 10𝐶1 0.2) 1 − 0.2 &DC)

+ 10𝐶2 0.2U 1 − 0.2 &DCU

= 0.3158
61
 Solution 4.1 cont’d.
OR compactly as:
d) 𝑃 2 < 𝑋 ≤ 5 = 𝑃 3 ≤ 𝑋 ≤ 5 = 𝑃 𝑋 = 3 + 𝑃 𝑋 = 4 +
𝑃 𝑋=5

= C 10𝐶𝑥 0.2% 1 − 0.2 &DC%

%X*
= 0.3158

e) 𝑃 𝑋 = 10 = 10𝐶10 0.2&D 1 − 0.2 &DC&D

= 1×0.2&D ×1 = 0.2&D
= 1.02×10CG
62
 Example 4.2
30% of students in college of engineering in a particular higher institution
travels to the central class by bus provided by the institute. To estimate
the probability of a certain fraction of a class in the college traveling to
class by bus, a lecturer chose fifteen students at random from this class in
the college.
a) Find the probability that only three students travel to class by bus.
b) Find the probability that less than five students travel to class by
bus.
c) Find the probability that not fewer than ten students travel to class
by bus.
d) Find the probability that at least ten students travel to class by bus.
e) Find the probability that between six and ten students travel to
class by bus.
f) Find the probability that at most five students travel to class by bus.
63
 Solution 4.2
Let 𝑋 be the number of students who travel to class by bus in
the class.
𝑝 = 30% = 0.3 and 𝑞 = 1 − 𝑝 = 70% = 0.7 𝑛 = 15.
=> 𝑋~𝐵(15, 0.3).
a) 𝑃 𝑋 = 3 = 15𝐶3 0.3* 1 − 0.3 &UC* = 0.1700
b) 𝑃 𝑋 < 5 = 𝑃 𝑋 ≤ 4 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 +
𝑃 𝑋 =3 +𝑃 𝑋 =4
= 15𝐶0 0.3D 1 − 0.3 &UCD + 15𝐶1 0.3& 1 − 0.3 &UC&
+ 15𝐶2 0.3( 1 − 0.3 &UC( +
15𝐶3 0.3* 1 − 0.3 &UC* + 15𝐶4 0.3) 1 − 0.3 &UC)
= 0.5155
64
 Solution 4.2 cont’d.
c) 𝑃 𝑋 ≥ 10 = 𝑃 𝑋 = 10 + 𝑃 𝑋 = 11 + 𝑃 𝑋 = 12 + 𝑃 𝑋 = 13 +
𝑃 𝑋 = 14 + 𝑃 𝑋 = 15
!#

= M 15𝐶𝑥 0.3' 1 − 0.3 !#+'

'/!&
= 0.0037

d) 𝑃 𝑋 ≥ 10 = 𝑃 𝑋 = 10 + 𝑃 𝑋 = 11 + 𝑃 𝑋 = 12 + 𝑃 𝑋 = 13 +
𝑃 𝑋 = 14 + 𝑃 𝑋 = 15
!#

= M 15𝐶𝑥 0.3' 1 − 0.3 !#+'

'/!&
= 0.0037
65
 Solution 4.2 cont’d.
e) 𝑃 6 < 𝑋 < 10 = 𝑃 𝑋 = 7 + 𝑃 𝑋 = 8 + 𝑃 𝑋 = 9
= 15𝐶7 0.3G 1 − 0.3 &UCG
+ 15𝐶8 0.3E 1 − 0.3 &UCE

+ 15𝐶9 0.3Y 1 − 0.3 &UCY

= 0.1275

f) 𝑃 𝑋 ≤ 5 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3 +
𝑃 𝑋 = 4 + 𝑃(𝑋 = 5)
= 15𝐶0 0.3D 1 − 0.3 &UCD
+ 15𝐶1 0.3& 1 − 0.3 &UC&
+ 15𝐶2 0.3( 1 − 0.3 &UC(
+ 5𝐶3 0.3* 1 − 0.3 &UC*
+ 15𝐶4 0.3) 1 − 0.3 &UC)
+ 15𝐶5 0.3U 1 − 0.3 &UCU
= 0.7216
66
 EXPECTATION AND VARIANCE OF BINOMIAL
DISTRIBUTION
The expectation (mean) and the variance of the binomial
distribution (𝑋~𝐵(𝑛, 𝑝)) are defined as:
• 𝑬𝒙𝒑𝒆𝒄𝒕𝒂𝒕𝒊𝒐𝒏 = 𝑬 𝑿 = 𝒏𝒑
• Varaince = 𝜎 ( = 𝑉𝑎𝑟 𝑋 = 𝑛𝑝 1 − 𝑝 = 𝑛𝑝𝑞 where 𝑞 = 1 − 𝑝

• 𝑆𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 = 𝜎 = 𝑆𝐷(𝑋) = Variance = 𝑛𝑝𝑞

67
 Example 4.3
• 10% of the articles from a certain production line are
defective. A sample of 25 articles is taken.
a) Find the expected number of defective articles.
b) Find the variance of the number of defective articles.
c) Find the standard deviation of the number of the
defective articles.

68
 Solution 4.3
• Let X be the number of defective articles.
• => 𝑋~𝐵(25, 0.1)
• 𝐸 𝑋 = 𝑛𝑝 = 25×0.1 = 2.5
• 𝑉𝑎𝑟 𝑋 = 𝑛𝑝𝑞 = 25×0.1× 1 − 0.1 = 25×0.1×0.9 = 2.25
• 𝑆𝐷 𝑋 = 𝑉𝑎𝑟(𝑋) = 2.25 = 1.5

• NB: Sometimes, the mean, variance or standard deviation

and probability of the binomial model, one or two of these
will be given and you will be asked to find 𝑝 and 𝑛.

69
 Example 4.4
• The random variable X is 𝐵(𝑛, 0.6) and 𝑃 𝑋 < 1 = 0.0256.
• Find the value of 𝑛.

Solution 4.4
• 𝑃 𝑋 < 1 = 𝑃 𝑋 = 0 = 𝑛𝐶0 0.6D 1 − 0.6 ACD
= 0.0256
• = 1×1×0.4A = 0.0256
• = ln 0.4A = ln 0.0256
Z[ D.D(U'
•𝑛= =4
Z[ D.)
• ∴ 𝑛 = 4 𝑎𝑛𝑑 𝑋~𝐵(4, 0.6)
70
 Example 4.5
• Each day a bakery delivers the same number of loaves to a
certain shop which sells 98% of them. Assuming that the
number of loaves sold per day has a binomial distribution
with a standard deviation of 7.
a) Find the number of loaves the shop would expect to sell
per day.
b) Find the probability that only 1% of the number of loaves
are sold per day.

71
 Solution 4.5
• Let 𝑋 be the number of loaves sold.
• => 𝑋~𝐵(𝑛, 0.98)
• 𝑆𝐷 𝑋 = 7 = 𝑛𝑝𝑞 = 𝑛×0.98×0.02
• => 0.0196𝑛 = 7(
)Y
•𝑛= = 2500
D.D&Y'
a) The shop would expect to sell 𝑛𝑝 = 2500×0.98 = 2450

1% of 2500 = 25
(U (UDDC(U
b) 𝑃 𝑋 = 25 = 2500𝐶25 0.98 1 − 0.98 =0
72
 THE POISSON DISTRIBUTION
• The Poisson distribution for a random variable, 𝑋, representing
the number of occurrence of an event in a given interval of
time, space or volume is defined by:
𝝀𝒙 𝒆C𝝀
𝑷 𝑿=𝒙 = 𝒇𝒐𝒓 𝒙 = 𝟎, 𝟏, 𝟐, 𝟑, … ∞
𝒙!
• Where, the mean and variance are equal.
𝑬(𝑿) = 𝝀 = 𝑽𝒂𝒓(𝑿)
NB:
• In some text, the mu, 𝜇, is used in place of lambda, 𝜆.
• The Poisson random variable takes values from 0 to infinity
unlike the Binomial model which takes values from 0 to 𝒏.
73
 PROBLEMS SUITABLE FOR THE POISSON R.V.
• The number of emergency calls received by an ambulance
control in an hour.
• The number of vehicles approaching a motorway toll bridge
in a five-minute interval.
• The number of flaws in a metre length of a material.
• The number of typed mistakes on a page of a book.
Conditions for a Poisson Model
• Events occur singly and at random in a given interval of time
or space.
• 𝜆, the mean number of occurrences in the given interval, is
74
known and is finite.
 Example 4.6
• Given that 𝑋 follows a Poisson probability distribution with 𝜆 =
2.5.
a) Find 𝑃(𝑋 = 10).
b) Find 𝑃(𝑋 ≤ 3).
c) Find 𝑃(𝑋 > 3).
d) Find 𝑃(𝑋 ≥ 5).
e) Find 𝑃(0 < 𝑋 < 4).

75
 Solution 4.6
𝑋~𝑃] (𝜆 = 2.5).
(.U !$
a) 𝑃 𝑋 = 10 = 𝑒 C(.U = 0.0002
&D!

b) 𝑃 𝑋 ≤ 3 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3
D & ( *
2.5 2.5 2.5 2.5
= 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U
0! 1! 2! 3!
= 0.7576

c) 𝑃 𝑋 > 3 = 1 − 𝑃 𝑋 ≤ 3 = 1 − 0.7576 = 0.2424

76
 Solution 4.6 cont’d.
d) 𝑃 𝑋 ≥ 5 = 1 − 𝑃 𝑋 ≤ 4
D & ( * )
2.5 2.5 2.5 2.5 2.5
= 1 − 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U
0! 1! 2! 3! 4!
= 1 − 0.8912
= 0.1088

e) 𝑃 0 < 𝑋 < 4 = 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3
& ( *
2.5 2.5 2.5
= 𝑒 C(.U + 𝑒 C(.U + 𝑒 C(.U
1! 2! 3!
= 0.6755
77
 Example 4.7
• On average the school photocopier breaks down eight times
during the school weak (Monday to Friday). Assuming that
the number of breakdowns can be modelled by a Poisson
distribution.
a) Find the probability that it breaks down five times in a
given week.
b) Find the probability that it breaks down not less than three
times in a given week
c) Find the probability that it breaks down once on Monday.
d) Find the probability that it breaks down eight times in a
fortnight.
78
 Solution 4.7
Let 𝑋 be the number of photocopier break down in a week.
=> 𝑋~𝑃] (𝜆 = 8).
%
CE E
a) 𝑃 𝑋 = 5 = 𝑒 = 0.0916
U!

b) 𝑃 𝑋 ≥ 4 = 1 − 𝑃 𝑋 ≤ 3
D & ( *
8 8 8 8
= 1 − 𝑒 CE + 𝑒 CE + 𝑒 CE + 𝑒 CE
0! 1! 2! 3!
= 1 − 0.0424
= 0.9576

79
 Solution 4.7 cont’d.
c) Here X cannot model the question because X occurrence
rate is weekly.
Let Y be the number of photocopier break down in a day.
E
𝑌~𝑃] (𝜆 = = 1.6).
U
&
1.6
𝑃 𝑌 = 1 = 𝑒 C&.' = 0.3230
1!

d) Let Z be the number of break downs in a fortnight.

𝑍~𝑃] (𝜆 = 2×8 = 16).
E
16
𝑃 𝑍 = 8 = 𝑒 C&' = 0.0120
80 8!
 EXPECTATION AND VARIANCE OF THE POISSON
The expectation (mean) and the variance of the Poisson
distribution (𝑋~𝑃] (𝜆)) are defined as:

• Expectation = 𝐸 𝑋 = 𝜆

• Variance = 𝜎 ( = 𝑉𝑎𝑟 𝑋 = 𝜆

• 𝑆𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛 = 𝜎 = 𝑆𝐷(𝑋) = Variance = 𝜆

81
 Example 4.8
• 𝑋 follows a Poisson distribution with standard deviation 4.
a) Find 𝑃(𝑋 = 0).
b) Find 𝑃(𝑋 < 3).
c) Find 𝑃(𝑋 > 3).
d) Find 𝑃(𝑋 ≥ 5).
e) Find 𝑃(0 < 𝑋 < 4).

82
 Solution 4.8
We need to find the Poisson rate, 𝜆.
Variance = Mean = Poisson rate = (Standard deviation)2
∴ 𝜆 = 4( = 16.
𝑋~𝑃] (𝜆 = 16).
$
C&' &'
a) 𝑃 𝑋 = 0 = 𝑒 = 1.13×10CG
D!

b) 𝑃 𝑋 < 3 = 𝑃(𝑋 ≤ 2) = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2
D & (
16 16 16
= 𝑒 C&' + 𝑒 C&' + 𝑒 C&'
0! 1! 2!
= 1.63×10CU
83
 Solution 4.8 cont’d.
c) 𝑃 𝑋 >3 =1−𝑃 𝑋 ≤3
16$ 16" 16% 16&
=1− 𝑒 !"# +𝑒 !"# +𝑒 !"# +𝑒 !"#
0! 1! 2! 3!
= 1 − 9.31×10!'
= 0.9999
d) 𝑃 𝑋 ≥5 =1−𝑃 𝑋 ≤4

!"#
16$ !"#
16" !"#
16% !"#
16& !"#
16(
=1− 𝑒 +𝑒 +𝑒 +𝑒 +𝑒
0! 1! 2! 3! 4!
= 1 − 0.0004
= 0.9996
e) 𝑃 0 < 𝑋 ≤ 4 = 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃 𝑋 = 3 + 𝑃(𝑋 = 4)
!"#
16" !"#
16% !"#
16& !"#
16(
=𝑒 +𝑒 +𝑒 +𝑒
1! 2! 3! 4!
= 0.0004

84
 THE SUM OF INDEPENDENT POISSON R.V.
For independent Poisson variables 𝑋 and 𝑌,
i.e. if 𝑋~𝑃] (𝜆& ) and 𝑌~𝑃] (𝜆( ),
Then:
• 𝑋 + 𝑌~𝑃] (𝜆& + 𝜆( )

85
 Example 4.9
• Given that 𝑋~𝑃] (4) and 𝑌~𝑃] (2.5).
a) Find 𝑃(𝑋 + 𝑌 = 3).
&
b) Find 𝑃(𝑋 − 0.5𝑌 > 2). OR 𝑃(𝑋 − 𝑌 > 2)
(

86
 Solution 4.9
a) Distribution of 𝑋 + 𝑌~𝑃] (4 + 2.5 = 6.5)
*
6.5
𝑃 𝑋 + 𝑌 = 3 = 𝑒 C'.U = 0.0688
3!

a) Distribution of 𝑋 − 0.5𝑌~𝑃] (4 − 0.5×2.5 = 2.75)

𝑃 𝑋 − 0.5𝑌 > 2 = 1 − 𝑃 𝑋 − 0.5𝑌 ≤ 2
D & (
2.75 2.75 2.75
= 1 − 𝑒 C(.GU + 𝑒 C(.GU + 𝑒 C(.GU
0! 1! 2!
= 1 − 0.4815
= 0.5185
87
 Example 4.10
• Telephone calls reach a secretary independently and at
random, internal ones at a mean rate of two in any five-
minute period, and external ones at a mean rate of one in
any five-minute period.
Calculate the probability that there will be more than two
calls in any period of two minutes.

88
 Solution 4.10
Let X and Y be internal and external number of calls reaching the
secretary respectively.
=> 𝑋~𝑃0 (2) and 𝑌~𝑃0 (1) for five-minute period.
"×" "
∴ for two minutes period, 𝑋~𝑃0 ( # = 0.8 ) and 𝑌~𝑃0 ( # = 0.4 )
Let T be total calls reaching the secretary.
=> 𝑋 + 𝑌 = 𝑇
Hence 𝑇~𝑃0 (0.8 + 0.4 = 1.2) in two minutes
𝑃 𝑇 >2 =1−𝑃 𝑇 ≤2
1.2 & 1.2! 1.2 "
= 1 − 𝑒 +!." + 𝑒 +!." + 𝑒 +!."
0! 1! 2!
= 1 − 0.8795
= 0.1205
89
 DISCRETE UNIFORM DISTRIBUTION
• A random variable 𝑋 has a discrete uniform distribution if
each of the 𝑛 values in it range, say, 𝑥& , 𝑥( , … , 𝑥A , has equal
probability.
• Then,
1
𝑃 𝑋 = 𝑥" =
𝑛
for 𝑖 = 1, 2, 3, … , 𝑛.

90
 Example 4.11
Consider modelling the toss of a die. The outcomes are:
{𝟏, 𝟐, 𝟑, 𝟒, 𝟓, 𝟔}
Each of these outcomes are equally likely to occur and hence
discretely uniform.
The probability for each outcome is defined as:
1
𝑃 𝑋 = 𝑑" =
6
for 𝑑" = 1, 2, 3, 4, 5, 6.

91
 Expectation, Second Moment and Variance of the
Discrete Uniform
&
• Mean = 𝐸(𝑋) = A (𝑡𝑜𝑡𝑎𝑙 𝑠𝑢𝑚 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑜𝑟 𝑣𝑎𝑙𝑢𝑒𝑠)

• Second moment =

(
1
𝐸 𝑋 = (𝑡𝑜𝑡𝑎𝑙 𝑠𝑢𝑚 𝑜𝑓 𝑠𝑞𝑢𝑎𝑟𝑒𝑑 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 𝑜𝑟 𝑠𝑞𝑢𝑎𝑟𝑒𝑑 𝑣𝑎𝑙𝑢𝑒𝑠)
𝑛
• Variance = 𝜎 ( = 𝑉𝑎𝑟 𝑋 = 𝐸 𝑋 ( − 𝐸 𝑋 (

92
 Using the die example 4.11 above:
& &U
• Mean = 1+2+3+4+5+6 = = 2.5
' '
& ( ( ( ( ( ( UU
• Second moment = 1 +2 +3 +4 +5 +6 =
' '
• Variance = Second moment − Mean(
UU ( *U
• Variance = − 2.5 =
' &(

93
 THE GEOMETRIC DISTRIBUTION
• Suppose you flip a coin several times. What is the probability
that the first head appears on the third toss? In order to
answer this question and other similar probability questions,
the geometric distribution can be used.
Conditions for a Geometric Model
For a situation to be described using a geometric model,
• Independent trials are carried out.
• The outcome of each trial is deemed either a success or a
failure.
• The probability, 𝑝, of a successful outcome is the same for
each trial.
94
 DISTRIBUTION OF GEOMETRIC PROBABILITY
• Assume the random variable, 𝑋, is the number of trials until a first
success, then 𝑋 is said to follow a Geometric Distribution.
• If 𝑋~𝐺𝑒𝑜 𝑝 , the probability that the first success is obtained at the
𝑥𝑡ℎ attempt is:
𝑃 𝑋 = 𝑥 = 𝑝𝑞 '+!
for 𝑥 = 1, 2, 3, 4, …
EXPECTATION AND VARIANCE OF THE GEOMETRIC
If 𝑋~𝐺𝑒𝑜(𝑝),
!
•𝐸 𝑋 =
3
4
• 𝑉𝑎𝑟 𝑋 =
3!
95
 Example 4.12
• The random variable 𝑋 is 𝐺𝑒𝑜(𝑝 = 0.35).
a) Find 𝑃(𝑋 = 4).
b) Find 𝑃(𝑋 > 4).
c) Find 𝑃(𝑋 ≤ 3).
d) Find the 𝐸(𝑋).

96
 Solution 4.12
𝑋~𝐺𝑒𝑜(0.35).
𝑝 = 0.35 and 𝑞 = 1 − 0.35 = 0.65
𝑃 𝑋 = 𝑥 = 𝑝𝑞 %C& .
a) 𝑃 𝑋 = 4 = 0.35×0.65* = 0.0961
b) 𝑃 𝑋 > 4 = 1 − 𝑃 𝑋 ≤ 4
= 1 − 0.35×0.65D + 0.35×0.65& + 0.35×0.65( + 0.35×0.65*
= 1 − 0.8215
= 0.1785
c) 𝑃 𝑋 ≤ 3 = 0.35×0.65D + 0.35×0.65& + 0.35×0.65(
= 0.7254
& &
d) 𝐸 𝑋 = =_ D.*U
= 2.8571
97
 NORMAL DISTRIBUTION
One of the most often used continuous probability distributions
is called the normal probability distribution. Many variables are
approximately normally distributed and can be represented
by the normal distribution
A random variable X with probability density function
- ( x - µ )2
1
f ( x) = e 2s 2
-¥<x<¥
2p s
is a normal random variable With mean and variance as;
E ( X ) = µ and V ( X ) = s 2
the notation N ( µ , s 2 ) is used to denote the distribution
98
 PROPERTIES OF A NORMAL MODEL
• It is bell-shaped.
• The mean, median, and mode are at the center of the
distribution.
• It is symmetric about the mean. (i.e. It is a reflection of itself if
a mean was placed at the center.)
• It is continuous; i.e., there are no gaps.
• It never touches the x axis (Asymptotic)
• The total area under the curve is 1 (100%).

99
 REPRESENTATION OF NORMAL MODEL
• The Normal distribution is made up of two parts and the
respective random variables are represented in brackets:
1. Standard Normal Distribution (𝑍)
2. Generalized Normal Distribution or
Normal Distribution (𝑋 or 𝑌 or any other variable except 𝑍)
NB:
• Given the difficult nature of integrating Normal Models, the 𝒁
is used to solve these complex integrations on a Table.
10
0
 Standard Normal Table (NEG. and POS. Values)

10
1
 DISTRIBUTION OF NORMAL DISTRIBUTION
• Standard Normal, 𝑍 is distributed with mean, 0 and variance,
1.

𝑍~𝑁(0,1)

• The Normal, 𝑋 is distributed with mean, 𝜇 and variance, 𝜎 ( .

𝑋~𝑁(𝜇, 𝜎 ( )

10
2
 Example 4.1B
• Given that 𝑋~𝑁(0,1), thus X follows the standard normal
distribution.
a) Find 𝑃 𝑍 < 1.2
b) Find 𝑃 𝑍 > 1.2
c) Find 𝑃 0.5 < 𝑍 < 1.2
d) Find 𝑃 𝑍 < 1.5
e) Find 𝑃 𝑍 > 1.23

10
3
 Solution 4.1B
a) 𝑃 𝑍 < 1.2 = 𝛷 1.20 = 0.8849

b) 𝑃 𝑍 > 1.2 = 1 − 𝑃 𝑋 ≤ 1.2

c) = 1 − 𝛷 1.20 = 1 − 0.8849
d) = 0.1151

10
4
 Solution 4.1B cont’d.
c) 𝑃 0.5 < 𝑍 < 1.2 = 𝛷 1.20 − 𝛷 0.50
d) = 0.8849 − 0.6915 = 0.1934

d) 𝑃 𝑍 < 1.5 = 𝑃 −1.5 < 𝑍 < 1.5

e) = 𝛷 1.50 − 𝛷 −1.50
f) = 0.9332 − 0.0668 = 0.8664
g) OR
h) = 𝛷 1.50 − 1 − 𝛷 1.50
i) = 2×𝛷 1.50 − 1
j) = 2×0.9332 − 1 = 0.8664
10
5
 Solution 4.1B cont’d.
e) 𝑃 𝑍 > 1.23 = 𝑃 𝑍 < −1.23 + 𝑃 𝑍 > 1.23
= 2 1 − 𝑃 𝑍 < 1.23 = 2 1 − 𝛷 1.23
=2×(1 − 0.8907) = 0.2186

10
6
 Finding the inverse of the standard normal
• The inverse is when we estimate the values instead of the
probabilities.
• 𝑃 𝑍 < 𝑎 = 0.50

• 𝑃 𝑍 < 𝑏 = 0.95

• That is finding the 𝑎 or 𝑏.

• Look for values that
give those probabilities.

10
7
 Example 4.2B
• Given that Z~𝑁(0,1), thus Z follows the standard normal
distribution.
Find 𝑎 in each of the following.
a) 𝑃 𝑍 < 𝑎 = 0.9
b) 𝑃 𝑍 > 𝑎 = 0.2
c) 𝑃 𝑎 < 𝑍 < 1.2 = 0.8
d) 𝑃 𝑍 < 𝑎 = 0.6372
e) 𝑃 𝑍 > 𝑎 = 0.82
f) 𝑃 −𝑎 < 𝑍 < 𝑎 = 0.95
10
8
 Solution 4.2B
a) 𝑃 𝑍 < 𝑎 = 0.9 => 𝛷 𝑎 = 0.9 => 𝑎 = 𝛷C& 0.9 = 1.28
Look for closest value to 0.9 (i.e. 0.9 − 0.8997 = 0.0003 and
0.9 − 0.9015 = 0.0015)
Hence 0.8997 (1.28) is closer to 0.9 than 0.9015 (1.29)

10
9
 Solution 4.2B cont’d.
b) 𝑃 𝑍 > 𝑎 = 0.2 => 1 − 𝑃 𝑍 < 𝑎 = 0.2 => 𝛷C& 0.8 = 𝑎
=> 𝑎 = 0.84.
Look for closest value to 0.8 (i.e. 0.8 − 0.7995 = 0.0005 and
0.9 − 0.8023 = 0.0023)
Hence 0.7995 (0.84) is closer to 0.8 than 0.8023 (0.85)

11
0
 Solution 4.2B cont’d.
c) 𝑃 𝑎 < 𝑍 < 1.2 = 0.8 => 𝛷 1.2 − 𝛷 𝑎 = 0.8
d) => 𝛷 𝑎 = 0.8849 − 0.8 = 0.0849
=> 𝑎 = 𝛷 C& 0.0849 = −1.37 (i.e. -1.37 is closer)

11
1
 Solution 4.2B cont’d.
d) 𝑃 𝑍 < 𝑎 = 0.6372
=>𝑃 −𝑎 < 𝑍 < 𝑎 = 0.6372
=>2×𝜙 𝑎 − 1 = 0.6372
&.'*G(
=>𝜙 𝑎 = => 𝑎 = 𝜙 C& 0.8186 = 0.91
(

11
2
 Solution 4.2B cont’d.
e) 𝑃 𝑍 > 𝑎 = 0.82
⇒ 𝑃 𝑍 > 𝑎 + 𝑃 𝑍 < −𝑎 = 0.82
⇒ 2× 1 − 𝜙 𝑎 = 0.82
D.E(
⇒𝜙 𝑎 =1−
(
⇒ 𝑎 = 𝜙 C& 0.59 = 0.23

11
3
 Solution 4.2B cont’d.
f) 𝑃 −𝑎 < 𝑍 < 𝑎 = 0.95 ⇒ 𝛷 𝑎 − 𝛷 −𝑎 = 0.95
&.YU
⇒ 2𝛷 𝑎 − 1 = 0.95 ⇒𝛷 𝑎 = (
⇒ 𝑎 = 𝛷 C& 0.9750 = 1.96

11
4
 GENERAL NORMAL PROBLEMS
• To standardize an X normal distribution with mean, 𝜇 and
variance, 𝜎 ( .

𝑥−𝜇
𝑍=
𝜎(
• Where 𝑥 is the value X assumes.
• For example: 𝑃(𝑋 < 𝑎).
#C`
• To standardize, this becomes: 𝑃 𝑍 <
a"

11
5
 Example 4.3B
• The random variable X is distributed N 20,9 .
(a) Find 𝑃 𝑋 < 22 .
(b) Find 𝑃(𝑋 ≥ 25).
(c) Find 𝑃 𝑋 < 17 .
(d) Find 𝑃 17 ≤ 𝑋 < 23 .

11
6
 Solution 4.3B
𝑋~𝑁(20,9).
a) 𝑃 𝑋 < 22
((C(D
•=𝑃 𝑍<
Y
• = 𝑃(𝑍 < 0.6667)
• = Φ 0.67 = 0.7486

11
7
 Solution 4.3B cont’d.
𝑋~𝑁(20,9).
b) 𝑃 𝑋 ≥ 25 = 1 − 𝑃 𝑋 < 25
(UC(D
• =1−𝑃 𝑍 <
Y
• = 1 − 𝑃(𝑍 < 1.6667)
• = 1 − Φ 1.67
• = 1 − 0.9525
• = 0.0475

11
8
 Solution 4.3B cont’d.
𝑋~𝑁(20,9).
c) 𝑃 𝑋 < 17
'FG#!
• =𝑃 𝑍<
H
• = 𝑃 𝑍 < −1
• = Φ −1 = 0.1587
d) 𝑃 17 ≤ 𝑋 < 23
#&G#! 'FG#!
• =𝑃 H
<𝑍< H
• = 𝑃 1 < 𝑍 < −1
• = Φ 1 − Φ −1
• = 0.8413 − 0.1587
11 • = 0.6826
9
 Example 4.4B
• The mean commuting time to work using the universal speed train
between an employee’s home and office is 24 minutes with 4
minutes of variation time. Assume the variable of time to
commute is normally distributed.
a) Find the probability that it takes an employee less than 19
minutes.
b) Find the probability that it takes an employee more than 20
minutes.
c) Find the probability that It takes an employee between 24 and
28 minutes to get to work.
d) Find the value of 𝑘such that 𝑃 𝑋 < 𝑘 = 0.2236
e) Find the value of 𝑘 such that 𝑃 𝑋 > 𝑘 = 0.1724
12
0
 Solution 4.4B
• Let 𝑋~𝑁(24,4)
&YC()
a) 𝑃 𝑋 < 19 = 𝛷 (
= 𝛷 −2.5 = 0.0062
(DC()
b) 𝑃 𝑋 > 20 = 1 − 𝑃 𝑋 < 20 = 1 − 𝛷 (
c) = 1 − 𝛷 −2
d) 1 − 0.0228 = 0.9772

12
1
 Solution 4.4B cont’d.
• Let 𝑋~𝑁(24,4)
(EC() ()C()
c) 𝑃 24 < 𝑋 < 28 = 𝛷 (
−𝛷 (
=𝛷 2 − 𝛷 0
= 0.9772 − 0.50000
= 0.4772

12
2
 Solution 4.4B cont’d.
• Finding the inverse of the normal distributed random variable
(d) 𝑃 𝑋 < 𝑘 = 0.2236
bC()
. => 𝛷 = 0.2236
(
bC() C&
. =𝛷 0.2236
(
=> 𝑘 − 24 = 2 −0.76
=> 𝑘 = 24 − 1.52 = 22.48

12
3
 Solution 4.4B cont’d.
• Finding the inverse of the normal distributed random variable
(e) 𝑃 𝑋 > 𝑘 = 0.1724 => 1 − 𝑃 𝑋 ≤ 𝑘 = 0.1724
bC()
𝑃 𝑋 ≤ 𝑘 = 0.8276 => 𝛷 = 0.8276
(
bC()
= 𝛷 C& 0.8276 = 0.945
(
.=> 𝑘 − 24 = 2 0.945
=> 𝑘 = 24 + 1.89 = 25.89

12
4
 Mean and Standard Deviation of Normal Dist.

Example 4.5B
The heights of piston rods produced by a manufacturer follow
a normal distribution with mean 𝜇 and standard deviation 6 m.
It is known that 4.78% of the pistons have heights greater than
82 m.
Find the value of the mean, 𝜇.

12
5
 Solution 4.5B
Let X be the height, in metres, of the piston rods.
𝑋~𝑁(𝜇, 6" ) and 𝑃 𝑋 > 82 = 0.0478
82 − 𝜇
𝑃 𝑋 > 82 = 1 − 𝑃 𝑋 < 82 = 1 − 𝑃 𝑍 < = 0.0478
6
82 − 𝜇
⇒𝑃 𝑍< = 1 − 0.0478 = 0.9522
6
82 − 𝜇
= 𝜙 +! 0.9522 = 1.667
6
82 − 𝜇 = 6×1.667
𝜇 = 82 − 6×1.667
𝜇 = 71.998
Therefore the mean is 72 m.
12
6
 Example 4.6B
• 𝑋~𝑁(100, 𝜎 #) and 𝑃 𝑋 < 106 = 0.8849.
• Find the value of the standard deviation, 𝜎.

Solution 4.6B
𝑋~𝑁(100, 𝜎 #) and 𝑃 𝑋 < 106 = 0.8849.
106 − 100
⇒𝑃 𝑍< = 0.8849
𝜎
106 − 100
= 𝜙 G' 0.8849
𝜎
106 − 100
= 1.2
𝜎
6 = 𝜎×1.2
6
𝜎= =5
1.2
12
7
 Example 4.7B
• In the collection of metallic rod parts of an engine using
robots, it is found that 20% have heights greater than 36.3cm
and 67% have heights greater than 29.9 cm.
Suppose the heights are normally distributed in this collection.
Find the mean and the standard deviation of the heights of
metallic rod collection procedure.

12
8
 Solution 4.7B
From the question, let 𝜇 𝑎𝑛𝑑 𝜎 be the mean and standard deviation
respectively
𝑃 𝑋 > 36.3 = 0.20 => 1 − 𝑃 𝑋 < 36.3 = 0.20 => 𝑃 𝑋 < 36.3 = 0.8
36.3 − 𝜇
𝛷 = 0.8 => 36.3 − 𝜇 = 𝜎𝛷 ,+ 0.8 = 0.84𝜎 … … … … … … . (1)
𝜎
𝑃 𝑋 > 29.9 = 0.67 => 1 − 𝑃 𝑋 < 29.9 = 0.67 => 𝑃 𝑋 < 29.9 = 0.33
29.9 − 𝜇
𝛷 = 0.33 => 29.9 − 𝜇 = 𝜎𝛷 ,+ 0.33 = −0.44𝜎 … … … … … … … . . (2)
𝜎
𝜇 + 0.84𝜎 = 36.3 …………………… 1
𝜇 − 0.44𝜎 = 29.9 … … … … … … … … . (2)
1.28𝜎 = 6.4 => 𝜎 = 5 and
𝜇 = 36.3 − 0.84 5 => 𝜇 = 32.1
Hence 𝜇 = 32.1 and 𝜎 = 5 respectively
12
9
 POISSON APPROXIMATION TO THE BINOMIAL
PROBABILITY DISTRIBUTION
• The use of binomial for the calculation of certain probabilities
becomes very cumbersome to handle when 𝑛 is very large
and the probability of success 𝑝, becomes very small. Hence,
the use of Poisson distribution to approximate the binomial
distribution in such instances.
• The condition for the approximation is when:
𝒏 ≥ 𝟓𝟎 and 𝒑 ≤ 𝟎. 𝟏, the binomial distribution 𝑿~𝑩(𝒏, 𝒑)
• can be approximated using a Poisson distribution with
𝝀 = 𝒏𝒑. i.e. 𝑿~𝑷𝒐 (𝒏𝒑).
13
0
 Example 5.1
• The random variable 𝑋 is 𝐵(75, 0.03).
Find;
(a) 𝑃(𝑋 = 0) (b) 𝑃(𝑋 = 2) (c) 𝑃(𝑋 ≤ 2)
using: Binomial distribution and Poisson distribution.

13
1
 Solution 5.1
Using binomial distribution, 𝑛 = 75 and 𝑝 = 0.03
GU
(a) 𝑃 𝑋 = 0 = D
0.03D 1 − 0.03 GUCD
= 0.1018
GU
(b) 𝑃 𝑋 = 2 = (
0.03( 1 − 0.03 GUC(
= 0.2703
(c) 𝑃 𝑋 ≤ 2 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2
75 D GUCD
75
= 0.03 1 − 0.03 + 0.03& 1 − 0.03 GUC&
0 1
75
+ 0.03( 1 − 0.03 GUC(
2
= 0.6083
13
2
 Solution 5.1 cont’d.
using Poisson, since 𝑛 > 50, i.e. 𝑛 = 75 and 𝑝 < 0.1 = 0.03, 𝜆 =
𝑛𝑝 = 75×0.03 = 2.25
=> 𝑋~𝑃] (2.25).
(.(U$ d &"."%
(a) 𝑃 𝑋 = 0 = = 0.1054
D!
(.(U" d &"."%
(b) 𝑃 𝑋 = 2 = (!
= 0.2668
(c) 𝑃 𝑋 ≤ 2 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2
2.25D 𝑒 C(.(U 2.25& 𝑒 C(.(U 2.25( 𝑒 C(.(U
= + +
0! 1! 2!
= 0.6093
13
3
 Example 5.2
• On average one in 200 cars breaks down on a certain stretch of
road per day.
a) Find the probability that, on a randomly chosen day, none of a
sample of 250 cars break down.
b) Find the probability that, on a randomly chosen day, three of a
sample of 250 cars break down.
c) Find the probability that, on a randomly chosen day, more than
two of a sample of 250 cars break down.
d) Find the probability that, on a randomly chosen day, between
three and six of a sample of 250 cars break down.
e) Find the probability that, on a randomly chosen day, less than
three of a sample of 250 cars break down.
f) Find the probability that, on a randomly chosen day, only five of
a sample of 250 cars break down.
13
4
 Solution 5.2
&
In the example, 𝑝 = (DD = 0.005 < 0.1 and 𝑛 = 250 > 50.
Hence Poisson approximation is applied. Assume 𝑋 models the
average break down
=> 𝑋~𝑃] (1.25) i.e. 𝜆 = 𝑛𝑝 = 250×0.005 = 1.25
&.(U$ d &!."%
(a) 𝑃 𝑋 = 0 = D!
= 0.2865
&.(U# d &!."%
(b) 𝑃 𝑋 = 3 = = 0.0933
*!
( &.(U( d &!."%
(c) 𝑃 𝑋 > 2 = 1 − 𝑃 𝑋 ≤ 2 = 1 − ∑%XD = 0.1315
%!

13
5
 Solution 5.2 cont’d.
(d) 𝑃 3 < 𝑋 < 6 = 𝑃 𝑋 = 4 + 𝑃(𝑋 = 5)
1.25) 𝑒 C&.(U 1.25U 𝑒 C&.(U
= + = 0.0364
4! 5!
(e) 𝑃 𝑋 < 3 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + 𝑃(𝑋 = 2)
1.25D 𝑒 C&.(U 1.25& 𝑒 C&.(U 1.25( 𝑒 C&.(U
= + + = 0.8685
0! 1! 2!
&.(U% d &!."%
(f) 𝑃 𝑋 = 5 = = 0.0073
U!

13
6
 NORMAL APPROXIMATION TO THE BINOMIAL
PROBABILITY DISTRIBUTION
• When 𝑋~𝐵(𝑛, 𝑝), then the
• Normal approximation can be used to estimate the binomial
probabilities provided
• 𝒏𝒑 > 𝟓 and 𝒏𝒒 > 𝟓.
NB: 𝑞 = 1 − 𝑝
• Hence 𝑋 becomes Normal i.e. 𝑿~𝑵(𝒏𝒑, 𝒏𝒑𝒒).

13
7
 CONTINUITY CORRECTION (CORRECTION
FACTOR)
• We use the correction factor when we are changing from
discrete probability to continuous probability.
1. 𝑃(𝑋 = 𝑘) → 𝑃(𝑘 − 0.5 < 𝑋 < 𝑘 + 0.5)
2. 𝑃(𝑋 ≤ 𝑘) → 𝑃(𝑋 < 𝑘 + 0.5)
3. 𝑃(𝑋 ≥ 𝑘) → 𝑃(𝑋 > 𝑘 − 0.5)
4. 𝑃(𝑚 ≤ 𝑋 ≤ 𝑛) → 𝑃(𝑚 − 0.5 < 𝑋 < 𝑛 + 0.5)
5. 𝑃(𝑋 < 𝑘) → 𝑃(𝑋 < 𝑘 − 0.5)
6. 𝑃(𝑋 > 𝑘) → 𝑃(𝑋 > 𝑘 + 0.5)
7. 𝑃(𝑚 < 𝑋 < 𝑛) → 𝑃(𝑚 + 0.5 < 𝑋 < 𝑛 − 0.5)
13
8
 Example 5.3
• The random variable X is distributed 𝐵 200,0.7 .
(a) Find 𝑃 𝑋 = 152 .
(b) Find 𝑃(𝑋 ≥ 130).
(c) Find 𝑃 𝑋 < 142 .
(d) Find 𝑃 136 ≤ 𝑋 < 148 .

13
9
 Solution 5.3
𝑋~𝐵(200,0.7).
𝑛𝑝 = 200×0.7 = 140 and 𝑛𝑞 = 200×0.3 = 60.
Since 𝑛𝑞 > 5 and 𝑛𝑞 > 5, use normal approximation with mean = 140 and
variance = 𝑛𝑝𝑞 = 200×0.7×0.3 = 42.
=> 𝑋~𝑁(140,42).
a) 𝑃 𝑋 = 152 → 𝑃 152 − 0.5 < 𝑋 < 152 + 0.5 = 𝑃 151.5 < 𝑋 < 152.5
'"'."G'*! '"#."G'*!
• =𝑃 *#
<𝑍< *#
• = 𝑃(1.7745 < 𝑍 < 1.9288)
• = Φ 1.93 − Φ 1.77
• = 0.9732 − 0.9616
• = 0.0116
14
0
 Solution 5.3 cont’d.
b) 𝑃 𝑋 ≥ 130 → 𝑃 𝑋 > 130 − 0.5 = 𝑃 𝑋 > 129.5
"%).'!"($
• =1−𝑃 𝑍 <
(%
• = 1 − 𝑃(𝑍 < −1.6202)
• = 1 − Φ −1.62
• = 1 − 0.0526
• = 0.9474

c) 𝑃 𝑋 < 142 → 𝑃 𝑋 < 142 − 0.5 = 𝑃 𝑋 < 141.5

"(".'!"($
• =𝑃 𝑍<
(%
• = 𝑃 𝑍 < 0.2315
• = Φ 0.23
• = 0.5910

14
1
 Solution 5.3 cont’d.
d) 𝑃 136 ≤ 𝑋 < 148 → 𝑃 136 − 0.5 < 𝑋 < 148 − 0.5
= 𝑃 135.5 < 𝑋 < 147.5
&*U.UC&)D &)G.UC&)D
•=𝑃 <𝑍<
)( )(
• = 𝑃 −0.6944 < 𝑍 < 1.1573
• = Φ 1.16 − Φ −0.69
• = 0.8770 − 0.2451
• = 0.6319

14
2
 Example 5.4
• At a particular car assembly company, records show that
each day, on average, only 80% of workers keep to their
schedule at the assembly floor. 250 records of these
schedules were randomly selected on a certain day.
a) Find the mean workers floor activities that are properly
scheduled.
b) Find the probability that more than 170 of workers keep
their schedules.
c) Find the probability that at least 200 workers keep their
schedules.
14
3
 Solution 5.4
Let 𝑋 be the number of workers who keep to their schedules.
=> 𝑋~𝐵(250, 0.8).
𝑛𝑝 > 250×0.8 = 200 and 𝑛𝑞 = 250×0.2 = 50
Hence 𝑋~𝑁(𝑛𝑝, 𝑛𝑝𝑞). i.e. 𝑛𝑝𝑞 = 250×0.8×0.2 = 40
a) 𝑀𝑒𝑎𝑛 = 𝑛𝑝 = 250×0.8 = 200.
b) 𝑃 𝑋 > 170 → 𝑃 𝑋 > 170 + 0.5 = 𝑃 𝑋 > 170.5
!5&.#+"&&
• =1−𝑃 𝑍 < %&
• = 1 − 𝑃 𝑍 < −4.6644
• = 1 − Φ(−4.66)
• =1−0=1
14
4
 Solution 5.4 cont’d.
c) 3𝑃 𝑋 > 200 → 𝑃 𝑋 > 200 + 0.5 = 𝑃 𝑋 > 200.5
(DD.UC(DD
• =1−𝑃 𝑍 <
)D
• = 1 − 𝑃 𝑍 < 0.0791
• = 1 − Φ(0.08)
• = 1 − 0.5319
• = 0.4681

14
5
 NORMAL APPROXIMATION TO THE POISSON
PROBABILITY DISTRIBUTION
• When 𝑋~𝑃] (𝜆), then the
• Normal approximation can be used to estimate the Poisson
probabilities provided
• 𝝀 > 𝟏𝟓.
• Hence 𝑋 becomes Normal i.e. 𝑿~𝑵(𝝀, 𝝀).

NB: 𝐸 𝑋 = 𝑉𝑎𝑟 𝑋 = 𝜆 for Poisson random variable X.

14
6
 Example 5.5
• Given that 𝑋~𝑃] (35).
a) Find the 𝑉𝑎𝑟[𝑋].
b) Find 𝑃 𝑋 = 37 .
c) Find 𝑃 𝑋 ≤ 33 .
d) Find 𝑃 𝑋 > 37 .
e) Find 𝑃 33 < 𝑋 < 37 .

14
7
 Solution 5.5
𝑋~𝑃] 𝜆 = 35 .
Since 𝜆 > 15, 𝑋~𝑁 35, 35 .
a) Var[X] = 𝜆 = 35
b) 𝑃 𝑋 = 37 → 𝑃 37 − 0.5 < 𝑋 < 37 + 0.5 = 𝑃 36.5 < 𝑋 < 37.5
*'.UC*U *G.UC*U
•=𝑃 <𝑍<
*U *U
• = 𝑃 0.2535 < 𝑍 < 0.4226
• = Φ 0.42 − Φ 0.25
• = 0.6628 − 0.5987
• = 0.0641
14
8
 Solution 5.5 cont’d.
c) 𝑃 𝑋 ≤ 33 → 𝑃 𝑋 < 33 + 0.5 = 𝑃 𝑋 < 33.5
&&.'!&'
• =𝑃 𝑍<
&'
• = 𝑃 𝑍 < −0.2535
• = Φ −0.25
• = 0.4013

d) 𝑃 𝑋 > 37 → 𝑃 𝑋 > 37 + 0.5 = 𝑃 𝑋 > 37.5

&+.'!&'
• =1−𝑃 𝑍 <
&'
• = 1 − 𝑃 𝑍 < 0.4226
• = 1 − Φ 0.42
• = 1 − 0.6628
• = 0.3372

14
9
 Solution 5.5 cont’d.
e) 𝑃 33 < 𝑋 < 37 → 𝑃 33 + 0.5 < 𝑋 < 37 − 0.5
= 𝑃 33.5 < 𝑋 < 36.5
**.UC*U *'.UC*U
•=𝑃 <𝑍<
*U *U
• = 𝑃 −0.2535 < 𝑍 < 0.2535
• = Φ 0.25 − Φ −0.25
• = 0.5987 − 0.4013
• = 0.1974

15
0
 Thank You.
Uploading materials from this course to websites that sell such content to students is prohibited by
integrity policies, and may also put you at risk for violating copyright policies

Jan 2021 Reference Slides-Mr. Emmanuel Harries, department of statistics and actuarial science knust,- Slides For Random
Variable And Probability Distributions