Continuous Probability distribution

Normal distribution/ Gaussian distribution/Normal curve

Normal distribution is a continuous probability distribution

Discussion on Normal Distribution

Frequency distribution p-67
The following are the frequency distribution of weights of 100
students .

Weight (kg)X Frequency (f)

60-62 5
63-65 18
66-68 42
69-71 27
72-74 8

Frequency distribution

X
60 67.45 74

Fig.1

Mean=  =67.45 kg.

Standard deviation =  =2.92 kg p-95

Binomial probability distribution

The probability of getting (0, 1, 2 ..…… 10) heads in 10 tosses are
(q+p)10= 10C0q10 p0 + 10C1q9 p1 + 10C2q8 p2 + 10C3q7 p3 + 10C4q6 p4 + 10C5q5 p5 +
10
C6q 4 p6 10 3 7 10
+ C7q p + C8q p + C9q p + C10q p
2 8 10 1 9 10 0 10

=P(0H)+ P(1H)+ P(2H)+ P(3H)+ P(4H)+ P(5H)+ P(6H)+ P(7H)+

P(8H)+ P(9H)+ P(10H)
1 10 45 120 210 252 210 120 45 10 1

=2 2 2 2
10 10
 10
 10
 10
 10
 10
 10
 10
 10

2 2 2 2 2 2 210

X 0 1 2 3 4 5 6 7 8 9 10
1 10 45 120 210 252 210 120 45 10 1
P(X) 210 210 210 210 210 210 210 210 210 210 210

Binomial probability distribution

Frequency distribution and Probability distribution both follow the

normal curve

Normal curve
Equation of the normal curve (given by Gauss) is
1  X  
2

1   
Y=f(X)= e 2  
where   mean and   s tan dard deviation
 2

The properties of the normal curve

1. The curve is maximum at

X 

2. The curve is symmetric about vertical axis through the mean 

2
 3. The curve has its point of inflection at X     ,
is concave downward if     X    

4. The total area under the curve and above the horizontal axis is
equal to 1

Area under the normal curve

The total area bounded by the curve and the X-axis is 1.

1  X  
2

1   
 
Normal curve Y= e 2
 2

3
    1  X   
2

1 2    X  1
Area=
 2 
e dX Let z 

dz 

dX

 z2
1  z 1
=
2 
e 2
dz Let t 
2
dt 
2
dz dz  2dt

1
e
t 2
= 2dt
2 

2


 e dt e
t 2
= t
dt 
2

 0 0
2
2 
=
 2
=1

z2
1 2
Y= e
2 is called standard normal curve

Area=1=total probability
So area of the normal curve represents probability

Standard normal curve

4
 z2
1 2
Y= e
2

Binomial Probability distribution is

P (X)= N C x p X q N  X X=0,1,2,…………….N

Poisson’s Probability distribution is

X e 
P(X)=   np X=0,1,2,…………….N
X!

Normal Probability distribution is given by

1  X  
2
X2
  
P(X1<X<X2)=  1 e 2   
dX
X1  2
X  1
Let z  dz  dX
 
z2
X 
z2
1 2
P(z1<z<z2) =  e dz X  X1 z1  1
z1 2 
X 
X  X2 z2  2


Ex.28 A coin is tossed 10 times. Find the probability of

getting (a) 3 heads (b) between 3 and 6 heads inclusive in
10 tosses of a fair coin by using
(i) binomial distribution
(ii) normal approximation to binomial distribution.

(a)(i)binomial distribution
7 3
 1   1  120
P(3)= 10
C3      10  0.1172
2 2 2

(a)(ii) Normal distribution

5
 1
  Np  10( )  5
2
1 1
  Npq  10( )( )  1.58
2 2
1  X  
2
X2
  
P(X1<X<X2)=  1 e 2   
dX
X1  2
z2 z2
1 2
P(z1<z<z2) =  e dz
z1 2

1  X  
2
 3.5 
P(2.5<X<3.5)=  1 e 2   
dX
2.5  2

0.114
z
-2 -1 0 1 2 3 3.9
-3.9 -3

-1.58 -0.95

Fig2

X1  
2.5  5
z1    1.58
 1.58
X   3.5  5
z2  2   0.95
 1.58
0.95 z2
1 2
P(-1.58<z<-0.95) =  e dz
1.58 2
Area between z1  1.58 and z 2  0.95
=(Area between z=0 and z=1.58)-(Area between z=0 and z=0.95)
=0.4429-0.3289

6
=0.114

Or,
0.95 z2
1 
P(-1.58<z<-0.95) =  e 2
dz  0.114
1.58 2

(b)(i) binomial distribution

Pr{between 3 and 6 heads inclusive}
=P(3)+ P(4)+ P(5)+ P(6)
7 3 6 4 5 5 4 6

= C3  1   1  + 10C4  1   1 
10
+
10 1
C5  
1
  +
1 1
C6    
10

2  2 2 2 2 2 2 2

120 210 252 210
 10  10  10  10
2 2 2 2
=0.1172+0.2051+0.2461+0.2051
=0.7735

(b)(ii)Normal distribution

1
  Np  10( )  5
2
1 1
  Npq  10( )( )  1.58
2 2
1  X  
2
X2
  
P(X1<X<X2)=  1 e 2   
dX
X1  2
z2 z2
1 2
P(z1<z<z2) =  e dz
z1 2

7
 Y

0.7718
z
-2 -1 0 1 2 3 3.9
-3.9 -3

-1.58 0.95

Fig 3

1  X  
2
6.5   
P(2.5<X<6.5)=  1 e 2  
dX
2.5 2
X   2.5  5
z1  1   1.58
 1.58
X   6.5  5
z2  2   0.95
 1.58
0.95 z2
1 2
P(-1.58<z<0.95) =  e dz
1.58 2
Area between z1  1.58 and z2  0.95
=(Area between z=0 and z=1.58)+(Area between z=0 and z=0.95)
=0.4429+0.3289
=0.7718

Or,
0.95 z2
1 
P(-1.58<z<0.95) =  e 2
dz  0.7718
1.58 2

8
 Ex.29 A manufacturer knows from experience that the resistance
of resistors is normally distributed with mean 100 ohms and
standard deviation 2 ohms. What percentage of resistors will have
resistance between 98 ohms and 102 ohms?

  100 ohms   2 ohms

X1=97.5 X2=102.5

X1   97.5  100
z1    1.25
 2

X2   102.5  100
z2    1.25
 2

z2 z2
1 2
P(z1<z<z2) =  e dz
z1 2
1.25 z2
1 2
P(-1.25<z<1.25) =  e dz
1.25 2

Area between z1  1.25 and z 2  1.25

=2( Area between z=0 and z=1.25)
=2x0.3944
=0.7888

0.7888
z
-2 -1 0 1 2 3 3.9
-3.9 -3

-1.25 1.25

9
 Fig4

Or,
1.25 z2
1 2
P(-1.25<z<1.25) =  e dz  0.7888  78.88%
1.25 2

10
This table is given at the end of your book.
It is shown upto 3.9 , last value is .5000

11
1 z2
1 2

0 2
e dz  ?

1.25 z2
1 2

0 2
e dz  ?

1.25 z2
1 2

1.25 2
e dz  ?

3.9 z2
1 2

3.9 2
e dz  ?

12