Normal Distribution

Definition
A random variable X is said to have a normal distribution with
parameters 𝜇 (mean) and 𝜎(standard deviation) if its density function is
given by
𝑥−𝜇 2
1 −
𝑓 𝑥 =𝜎 ⅇ 2𝜎2 ; −∞ < 𝑥 < ∞
2𝜋

where
e = 2.712
𝛱 = 3.14
 Characteristics of the Normal Distribution
(1) It is a symmetrical distribution
(2) It has two parameters 𝜇 and 𝜎
(3) It has maximum probability occurring at the X = 𝜇
(4) It has equal mean, median and mode
(5) The values of 𝛽1 and 𝛽2 are 0 and 3 respectively
(6) The proportions of area lying between 𝜇 ± 𝜎, 𝜇 ± 2𝜎 and 𝜇 ± 3𝜎
respectively 68.27%, 95.45% and 99.73%.
 Normal Distribution
Definition
A random variable X is said to have a normal distribution with
parameters 𝜇 (mean) and 𝜎(standard deviation) if its density function is
given by
𝑥−𝜇 2
1 −
𝑓 𝑥 =𝜎 ⅇ 2𝜎2 ; −∞ < 𝑥 < ∞
2𝜋

where
e = 2.712
𝛱 = 3.14
 Standardized Normal Distribution
Definition
If X is a normal variate with mean µ and standard deviation σ, then
𝑋−𝜇
𝑧= will also be a normal variate with mean zero and standard
𝜎
deviation unity. Then, the distribution of z is called standardized
normal distribution and the probability density function is given by
𝑧2
1 −
𝑓 𝑧 = ⅇ 2 ; where, µ = 0, 𝜎 2 = 1 and e = 2.712, 𝛱 = 3.14
2𝜋
It is symmetric about z = 0
 Have you seen this shape before?

-4 -3 -2 -1 0 1 2 3 4
Have you seen this shape before?
Have you seen this shape before?
 The Normal Distribution
Oftentimes data is described as being “normal” (in the statistical sense); but
what does that mean?

Let’s begin by talking about the frequency by which some events occur; both
natural and man-made
 Natural: human height, temperature, blood-pressure etc.
 Man-made: Machine Products, financial data, sales etc.

For these measures, the average (mean) tends to be very frequent while
measures away from the mean are less and less frequent

Let’s take a look at the normal distribution to learn more about its
properties.
 Normal Distribution
Definition
A random variable X is said to have a normal distribution with
parameters 𝜇 (mean) and 𝜎(standard deviation) if its density function is
given by
𝑥−𝜇 2
1 −
𝑓 𝑥 =𝜎 ⅇ 2𝜎2 ; −∞ < 𝑥 < ∞
2𝜋

where
e = 2.712
𝛱 = 3.14
 Probability Area

Lower tail P Upper tail

µ
Position Position
µ = -12.3 µ=0 µ = 10

Mean can be any numerical value

Slides distribution Side- to - Side

σ
σ : Larger (widen)

Standard Deviation
 The Standard Normal Curve

Area Under the curve: Z distribution

 
4 3 2 1 0 1 2 3 4
 The Standard Normal Curve

U
p
50% p
.50 e
r

Cumulative Probability b

   z  0  0.5 o
u
n

4
d

3 2 1 0 1 2 3 4

 The Standard Normal Curve

Cumulative Probability
 z 10.1587
U
p
p
e
15.87% r

.1587 b
o
u
n

  
d

4 3 2 1 0 1 2 3 4
 The Standard Normal Curve
.5000
Z Cumulative
Probability
-3 0.0013
-2 0.0228
.1587
-1 0.1587 .8413
0 0.5000
1 0.8413
2 0.9772 .0228
.9772
3 0.9987
.0013
.9987

 
4 3 2 1 0 1 2 3 4
 The Standard Normal Curve
p ( 1  z  0 )  0.3413 .5000
Z interval
Z Cumulative -3
Probability 0.0214
-3 0.0013
.1587 -2
-2 0.0228 .8413 0.1359
-1 0.1587
0.3413 0.3413 -1
0 0.5000 .5 - .1587
0.3413
1 0.8413 .0228
.9772 0
2 0.9772
0.1359 0.1359 0.3413
3 0.9987 .0013
.9987 1
0.0214 0.0214
  0.1359
4 3 2 1 0 1 2 3 4 2
0.0214
3
 p ( 1  z  1)  .6826

-1σ 68.26% -1σ

4 3 2 1 0 1 2 3 4
 p ( 2  z  2)  .9544

-2σ 95.44% -2σ

4 3 2 1 0 1 2 3 4
 p ( 3  z  3)  .9974

-3σ 3σ

95.44%
99.74%
.9544
.9974

4 3 2 1 0 1 2 3 4
Have you seen this shape before?
Problem1.
A battery has a lifetimes which are normally distributed with a mean of 62
hours and a standard deviation of 3 hours. What is the probability of a battery
lasting less than 68 hours?
Solution µ σ2

Let, X be the random variable “lifetime in hours” where X ~ N(62, 9)

𝑥−𝜇
𝑍=
𝜎
X 68 −62
62 68=x =
3
Z ~ N(0, 1) =2
Now, P(X<68) = P(Z<2) = 0.977
0 z
Problem2
The masses of a well known brand of breakfast cerial are normally distributed
with mean of 250g and standard deviation of 4g. Find the probability of a
packet containing more than 254.4g.
Solution µ σ2
Let, X be the random variable “mass of cerial in grams” where X ~ N(250, 4)

𝑥−𝜇
𝑍=
𝜎
X 254.4 −250
250 254.4=x =
4
= 1.1 Now, P(X>254.4) = P(Z>1.1)
Z ~ N(0, 1)
= 1- P(Z<1.1)
Z
= 1- 0.8643
0 z
= 0.136
Problem3.
A carton of orange juice has a volume which is normally distributed with a mean
of 120 ml and a standard deviation of 1.8 ml. Find the probability that the volume
is more than 118 ml.
Problem4.
A light bulb has lifetimes which are distributed with a mean of 520 hours and a
standard deviation of 6 hours. What is the probability of a light bulb lasting less
than 511 hours?