0% found this document useful (0 votes)
179 views20 pages

Class 3 - Normal Distribution

The document discusses the normal distribution, which is a continuous probability distribution that has a bell-shaped curve. It defines the normal distribution and standard normal distribution, and describes their key characteristics like mean, median and mode coinciding. It also provides examples and formulas to calculate probabilities for the normal distribution.

Uploaded by

kabbilaash kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
179 views20 pages

Class 3 - Normal Distribution

The document discusses the normal distribution, which is a continuous probability distribution that has a bell-shaped curve. It defines the normal distribution and standard normal distribution, and describes their key characteristics like mean, median and mode coinciding. It also provides examples and formulas to calculate probabilities for the normal distribution.

Uploaded by

kabbilaash kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 20

0.

22

Normal Distribution
.
2
.
1
0
0.00
-5 5
Definition 0.22

A Continuous random variable X is said to follow a .


normal distribution with mean 𝝁 and variance 𝝈𝟐 and 2
.
its probability density function is given by, 1
0.00
0 -5 5

1 𝑥−𝜇 2
1 −
𝑓 𝑥 = 𝑒 2 𝜎 ~N(𝝁, 𝝈𝟐 ) where -∞< 𝑥, μ < ∞, 𝜎 > 0
𝜎 2𝜋
Standard Normal Distribution:
A Normal distribution whose mean is 0 and variance is 1.

𝑍2
1 − 𝒙−𝝁
𝑓 𝑧 = 𝑒 2 ~N(𝟎,𝟏) , where -∞< 𝑧 < ∞ and 𝒁=
2𝜋 𝝈
Note :
Mean and Variance of Normal distribution is :𝝁 and 𝝈𝟐
Standard deviation of Normal distribution is : 𝝈
Mean and Variance of Standard Normal distribution is: 0 & 1
0.22

.
Characteristics of Normal distributions: 2
.
1
0.00
0 -5 5

The Curve is bell shaped and symmetrical curve


about the line x=μ
Mean, Median and mode of the distribution are
coincide.
Since f(x) being the probability, can never be
negative.
P(-∞<Z< ∞) =1
Area Property: P(-∞<Z< 0) =0.5
P(0 <Z< ∞) =0.5
 P(μ-σ<X<μ+σ) = .6826 0.5 0.5

 P(μ-2σ<X<μ+2σ) = .9544
 P(μ-3σ<X<μ+3σ) = .9973 ∞- 0 ∞
STATISTICAL TABLE –NORMAL DISTRIBUTION (0r) Z Test
STATISTICAL TABLE –NORMAL DISTRIBUTION (0r) Z Test
Example
The average seasonal rainfall in a place is 16 inches with a
0.22

.
standard deviation of 4 inches. What is the probability 2
that in a year the rainfall in that place will be between 20 .
and 24 inches? 1
0.00
0 -5 5

Answer:
Given mean (𝝁)=16 inches and Standard deviation (𝝈)= 4 inches
𝒙−𝝁 𝒙−𝟏𝟔
The Normal Variate 𝒁= , 𝒁=
𝝈 𝟒0.22
To find P(20≤x≤24) :

𝟐𝟎−𝟏𝟔 𝟐𝟒−𝟏𝟔
P( <𝐙< ) = P(1< 𝑍 <2)
𝟒 𝟒

= P(0< 𝑍 <2) - P(0 < 𝑍 <1)

= .4772 – 0.3413

= 0.1359 0.00
-5 5
10 2
Example
The weekly wages of 1000 workmen are normally 0.22

.
distributed around a mean of Rs.70 with a standard 2
deviation of Rs.5. Estimate the number of workers whose .
weekly wages will be (i) More than Rs.72 (ii) Less than 1
0.00

Rs.69 (iii) Between Rs.69 and Rs.72


0 -5 5

Answer:
Given mean (𝝁)=70 inches and Standard deviation (𝝈)= 5 inches
𝒙−𝝁 𝒙−𝟕𝟎
The Normal Variate 𝒁 = , 𝒁=
𝝈 𝟓
(i) To find P(More than Rs.72): P (X>72)
𝑷(𝑿 > 𝟕𝟐) = 𝑷 𝒁 > 𝟎. 𝟒 = 𝟎. 𝟓 − 𝑷(𝟎 < 𝒁 < 𝟎. 𝟒) = 0.5 – 0.1554 = 0.3446
Out of 1000 workmen, the number of workers whose wages are greater
than 72 is = 1000 * 𝑷(𝑿 > 𝟕𝟐) = 344.6 ≃ 345
(ii) To find P(Less than Rs.69): P (X<69)
𝑷(𝑿 < 𝟔𝟗)= 𝑷(𝒁 < −𝟎. 𝟐) = 𝟎. 𝟓 − 𝑷 𝟎 < 𝒁 < 𝟎. 𝟐 = 0.5 -0.0793 = 0.4207
Out of 1000 workmen, the number of workers whose wages are less than
69 is = 1000 * 𝑷(𝑿 < 𝟔𝟗) = 420.7 ≃ 421
(ii) To find P(69<X<72):
𝑷(𝟔𝟗 < 𝑿 < 𝟕𝟐)= 𝑷(−𝟎. 𝟐 < 𝒁 < 𝟎. 𝟒) = 0.0793+0.1554 = 0.2347
Out of 1000 workmen, the number of workers whose wages are lies between
Rs.69 and Rs.72 is = 1000 * 𝑷(𝟔𝟗 < 𝑿 < 𝟕𝟐)= 234.7 ≃ 235
Using Spread Sheets to Compute
Normal Distributions 0.22

.
2
Format of Normal distribution in Excel: .
1
0.00
0
=NORM.DIST (x, mean, SD, False)
-5 5

A B C
Mean SD
1 2000 500
2 3 Sigma Values Probability
3 Probability f (x )
4 3 3000 =NORM.DIST(B4,B$1,C$1,FALSE)
5 2.9 3500 =NORM.DIST(B5,B$1,C$1,FALSE)
6 2.8 4000 =NORM.DIST(B6,B$1,C$1,FALSE)
7 2.7 4500 =NORM.DIST(B7,B$1,C$1,FALSE)
8 2.6 5000 =NORM.DIST(B8,B$1,C$1,FALSE)
9 2.5 5500 =NORM.DIST(B9,B$1,C$1,FALSE)
Normal Distribution 0.22

.
2
.
1
0.00

Normal Distributions 0 -5 5

0.0009

0.0008

0.0007

0.0006
PROBABILITY OF X

0.0005

0.0004

0.0003

0.0002

0.0001

0
0 500 1000 1500 2000 2500 3000 3500 4000
X
0.22

Sigma =  = Deviation .
2
.
1
0.00
0 -5 5

-3
-7
-6
-5
-4

-2
-1

7
1
2
3

6
0

4
between + / - 1 68.27 %

between + / - 2 95.45 %


between + / - 3 99.73 %

between + / - 4 99.9937 %


between + / - 5 99.999943 %

between + / - 6 99.9999998 %


Comparison Between 3 σ and 6 σ
The 3 sigma Company The 6 sigma Company
0.22

.
2
 Spends 15~25% of  Spends 5% of sales .
sales dollars on cost of dollars on cost of 1
failure failure
0.00
0 -5 5

 Relies on inspection to  Relies on capable


find defects process that don’t
produce defects
 Does not have a  Use Measure, Analyze,
disciplined approach to Improve, Control and
gather and analyze Measure, Analyze,
data Design
 Benchmarks themselves  Benchmarks themselves
against their against the best in the
competition world
 Believes 99% is good  Believes 99% is
enough unacceptable
0.22

.
APPLICATION OF NORMAL DISTRIBUTIONS: 2
.
1
0.00
0 -5 5

Real Life – Achievements made by


students based on different
methodology followed in teaching.

Calculation of errors made by chance in


experimental measurements.

Engineering field in experiments


conducted by varying the conditions
0.22

.
APPLICATION OF NORMAL DISTRIBUTIONS: 2
.
1
0.00
0
Business Field – Prices of Commodity,
-5 5

Effects of Advertising, man power


handling based on stress management.

Computation of hit probability of a shot

Seasonality and cyclic issues

Statistical inference in almost every


branch of science.
Example
X is a normal variate with means 30 and S.D is 5. Find
0.22

.
the following (i) P(2𝟔 < 𝐗 <40) (ii) P(𝐗 >45) 2
.
1
0.00
0 -5 5

Answer:
Given mean (𝝁)=30 and Standard deviation (𝝈)= 5
𝒙−𝝁 𝒙−𝟑𝟎
The Normal Variate 𝒁= , 𝒁=
𝝈 𝟓
(i) To find P(X>45) :
𝟒𝟓−𝟑𝟎
P(X>45) ⇒ P(Z> 𝟓 )
P(Z>0.3) = 0.5 – 0.4987 = 0.0013

(ii) To find P(2𝟔 < 𝐗 <40):

P(2𝟔 < 𝐗 <40) = P(-0.8 < 𝑍 <2) = P(0< 𝑍 <0.8) +P(0 < 𝑍 <2)
= 0.2881+0.4772 = 0.7653
Example
A Normal distribution has mean 𝝁=20 and standard
0.22

.
deviation 𝝈=10 . Find the value of P(15≤x ≤40). 2
.
1
0.00
0 -5 5

Answer:
Given mean (𝝁)=20 and Standard deviation (𝝈)= 10
𝒙−𝝁 𝒙−𝟐𝟎
The Normal Variate 𝒁= , 𝒁=
𝝈 𝟏𝟎
To find P(15≤x≤40) :

𝟏𝟓−𝟐𝟎 𝟒𝟎−𝟐𝟎
P( <𝐙< ) = P(-0.5 < 𝑍 <2)
𝟏𝟎 𝟏𝟎

= P(-0.5 < 𝑍 <0) +P(0 < 𝑍 <2)

= P(0< 𝑍 <0.5) +0.4772 = 0.1915+0.4772

= 0.6687
Example
A manufacturer produces air mail envelopes whose weight
0.22

.
is normal with mean 1.950 gm and standard deviation is 2
0.025 gm. The envelopes are sold in lots of 1000. How .
many envelopes in a lot may be heavier than 2 grams? 1
0.00
0 -5 5

Answer:
Given mean (𝝁)=1.950 gm and Standard deviation (𝝈)= 0.025 gm
𝒙−𝝁 𝒙−𝟏.𝟗𝟓
The Normal Variate 𝒁= , 𝒁=
𝝈 𝟎.𝟎𝟐𝟓
To find P(X>2):

= P(Z > 2) = 0.5 – P(0< 𝑍 <2)

= 0.5 – 0.4772

= 0.0228

Out of 1000, the number of envelopes heavier than 2 is


= 1000* P(X>2) =23
Example
In test of 2000 bulbs electric bulbs, it was found that the 0.22

.
life of a particular make, was normally distributed with an 2
average life of 2040 hours and standard deviation of 60 .
hrs. Estimate the number of bulbs likely to burn for (i) 1
0.00

More than 2150 hrs (ii) Less than 1950 hrs (iii) more
0 -5 5

than 1920 but less than 2160 hrs.


Answer:
Given mean (𝝁)=2040 hrs and Standard deviation (𝝈)= 60 hrs
𝒙−𝝁 𝒙−𝟐𝟎𝟒𝟎
The Normal Variate 𝒁 = , 𝒁=
𝝈 𝟔𝟎𝟓
(i) To find P(More than 2150 hrs): P (X>2150)
𝑷(𝑿 > 𝟐𝟏𝟓𝟎) = 𝑷 𝒁 > 𝟏. 𝟖𝟑𝟑 = 𝟎. 𝟓 − 𝟎. 𝟒𝟔𝟔𝟒 = 𝟎. 𝟎𝟑𝟑𝟔
The number bulbs expected to burn for more than 2150 hrs: 67
(ii) To find P(Less than R1950 hrs): P (X<1950)
𝑷 𝑿 < 𝟏𝟗𝟓𝟎 = 𝑷 𝒁 < −𝟏. 𝟓 = 𝟎. 𝟓 − 𝟎. 𝟒𝟑𝟑𝟐 = 𝟎. 𝟎𝟔𝟔𝟖
The number bulbs expected to burn for less than 1950 hrs: 134
(ii) To find P(1920<X<2160):
𝑷 𝟏𝟗𝟐𝟎 < 𝑿 < 𝟐𝟏𝟔𝟎 = 𝑷 −𝟐 < 𝒁 < 𝟐 = 𝟐𝑷 𝟎 < 𝒁 < 𝟐 =0.9546
The number bulbs expected to burn lies between 1920 and 2160 is 1909
Example
In a normal distribution 31% of the items are under 45
0.22

.
and 8% are over 64. Find the mean and the standard 2
deviation. .
1
0.00
0 -5 5

Answer:
0.22

The Value of Z corresponding to the area


0.19 is 0.5 nearly. 𝑷(𝑿 < 𝟒𝟓)

𝟒𝟓−μ
Z= =-0.5⇒ -0.5 σ+ μ = 45 ----- 1
σ
The Value of Z corresponding to the area 0.42
0.42 is 1.4 nearly. 𝑷(𝑿 > 𝟔𝟒) 0.19

𝟔𝟒−μ
Z= =1.4⇒ 1.4 σ+ μ = 64 --------- 2 0.31 0.08
σ 0.00
-5 5
From equation 1 & 2 , we get 𝝁 = 50 and 𝝈 =10
Example
In a distribution exactly normal, 7% of the items are
0.22

.
under 35 and 89% are under 63. What are the mean and 2
the standard deviation of the distribution? .
1
0.00
0 -5 5

Answer:
0.22

The Value of Z corresponding to the area


0.43 is 1.47 nearly. 𝑷(𝑿 < 𝟑𝟓)

𝟑𝟓−μ
Z= =-1.47 ⇒ -1.47σ+ μ = 35 ----- 1
σ
The Value of Z corresponding to the area 0.39
0.39 is 1.23 nearly. 𝑷(𝑿 < 𝟔𝟑) 0.43

𝟔𝟑−μ
Z= =1.23⇒ 1.23 σ+ μ = 63 --------- 2 0.07 0.11
σ 0.00
-5 5
From equation 1 & 2 , we get 𝝁 = 50.288 and 𝝈 =10.36

You might also like