Vous êtes sur la page 1sur 10

MODULE IV

PROBABILITY DISTRIBUTION
BINOMIAL DISTRIBUTION
A random variable X is said to follow binomial distribution with parameters n & p if P
( X ) = nCx p x q n x where x = 0 , 1,2,3 ..n , p is the probability of success & q is the
probability of failure and q = 1 p and p(x) is called the probability density function.
Note
n
For a binomial distribution p(x) = 1
x=0
Proof
n
p(x) = nC0 p 0 q n-0 + nC1 p1 q n- 1 + nC2 p2 q n-2 +..+ nCn pn q n-n
x=0
= q n + nC1 p1 q n- 1 + nC2 p2 q n-2 +..+ pn
= ( p + q )n
=1
In a binomial distribution
1 ) n , the number of trials is finite.
2 ) each trial has two possible outcomes called
success & failure.
3)all the trials are independent
4) p & hence q is constant for all the trials.

Mean and Variance of a binomial distribution

Mean = = x p(x)
p(x)
But for Binomial distribution p(x) = 1
= x p(x)
= x nCx p x q n x
= 0. nC0 p 0 q n-0 +1. nC1 p1 q n- 1 +2. nC2 p2 q n-2 +..+ n.nCn pn q n-n
= np1 q n- 1 +n(n-1)p2 q n-2 +..+ n pn
= np(q n- 1 + (n-1)p q n-2 +..+ p n-1)
= np( q + p ) n-1
= np
Mean = = np

Variance = 2 = x 2 p(x) 2
p(x)
But for the binomial distribution p(x) = 1

2 = x 2 p(x) 2
= 0. nC0 p 0 q n-0 +1. nC1 p1 q n- 1 +4. nC2 p2 q n-2 +..+ n 2.nCn pn q n-n (n2p2)
= np1 q n- 1 +2n(n-1)p2 q n-2 + 3 /2n(n-1)(n-2) p3q n-3..+ n 2 pn - n 2p 2

= np (q n- 1 +2 (n-1)p q n-2 +3 /2 (n-1)(n-2) p2q n-3..+ n p n-1 )- n 2p 2

= np[ (q n- 1 + ( n-1)p q n-2 +1 /2 (n-1)(n-2) p2q n-3..+ p n-1 )

+(( n-1)p q n-2 +1 (n-1)(n-2) p2q n-3..+ (n-1) p n-1) ] -n 2p 2

= np[( q + p ) n-1 +( n-1)p (q n-2 + (n-2) pq n-3..+ p n-2)] -n 2p 2

= np [ ( q + p ) n-1 +( n-1)p(q + p ) n-2] -n 2p 2

= np [ ( q + p ) n-1 +( n-1)p(q + p ) n-2] -n 2p 2

= np ( 1+ (n-1)p) -n 2p 2

= np + n 2p2 n p 2 n 2p 2
= np(1 p)
= npq
Standard deviation = npq

Problems
1 ) The mean and variance of a binomial variate are 16 & 8. Find i) P (X= 0)
ii) P( X 2)

Mean = = np = 16
Variance = 2 = npq = 8

npq / np = 8/16 = 1/2


ie, q =
p=1q=
np = 16 ie, n = 32

i) P ( X = 0 ) = nC0 p 0 q n-0
= ()0 (1/2)32
= (1/2)32

ii)P( X 2) = 1 P ( X < 2)
= 1 P( X = 0 ,1)
= 1 P(X = 0) P(X = 1)
= 1- 33 (1/2)32
2) Six dice are thrown 729 times.Howmany times do you expect atleast 3
dice to show a 5 or 6 ?
Here n = 6 ,N = 729
P(x 3) = 6Cx px q n-x
Let p be the probability of getting 5 or 6 with 1 dice
ie, p = 2/6 = 1/3
q = 1 1/3 = 2/3
P(x 3) = P ( x = 2,3,4,5,6)
= p( x=3)+p(x=4)+p(x=5)+p(x=6)
=0 .3196
number of times = 729*0.3196 = 233
3)A basket contains 20 good oranges and 80 bad oranges . 3 oranges
are drawn at random from this basket . Find the probability that out
of 3 i) exactly 2 ii)atleast 2 iii)atmost 2 are good oranges.
Let p be the probability of getting a good orange
ie, p =80C1
100C1
= 0.8
q = 1- 0.8 = 0.2
i ) p (x=2) = 3C2 (0.8)2(0.2)1 = 0.384
ii) p(x2) = P(2) +p(3)= 0.896
iii) p(x 2) = p(0) +p(1) + p(2) = 0.488
4) In a sampling a large number of parts manufactured by a machine , the
mean number of defective in a sample of 20 is 2. Out of 1000 such
samples howmany would expected to contain atleast 3 defective parts.
n=20 n p =2
ie , p=1/10 q = 1-p = 9/10

p(x 3) = 1 p ( x < 3 )
= 1 p( x = 0,1,2) = 0.323
Number of samples having atleast 3 defective parts = 0.323 * 1000
= 323
Home work

1 ) Assume that on the average 1 telephone number out of 15 called between


2 pm and 3pm on a week day is busy. What is the probability that if 6 m
randomly selected numbers are called i) not more than 3 will be busy
ii) atleast 3 of them will be busy.
2) If 10% of bolts produced by a machine are defective . Determine the
probability that out of 10 bolts, chosen at random i) one ii)none iii)atmost
2 bolts will be defective.
3) In 800 families with 5 children each , howmany families would be
expected to have i) 3 boys and 2 girls ii)atmost 2 girls.iii) no girl
( Assume the probability for boys & girls tobe equal.)
4) During a war 1 ship out of 9 was sunk on an average in making a certain
voyage. Find the probability that exactly 3 out of a convoy of 6 ships
would arrive safely.
5) In a large consignment of electric bulbs 10 percent are defective. A
random sample of 20 is taken for inspection . Find the probability that
i) all are good bulbs ii) at most there are 3 defective bulbs. iii) Exactly
there are 3 defective bulbs.

FITTING OF BINOMIAL DISTRIBUTION

The process of determining the most appropriate values of the parameters from the
given observations and writing down the probability distribution function is known as
fitting of the binomial distribution.

Problems
1) Fit an appropriate binomial distribution and calculate the theoretical distribution
x: 0 1 2 3 4 5
f: 2 14 20 34 22 8

Here n = 5 , N = 100

Mean = xi fi = 2.84
fi

np = 2.84
p = 2.84/5 = 0.568
q = 0.432

p(r) = 5Cr (0.568)r (0.432) 5-r , r = 0,1,2,3,4,5


Theoretical distributions are

r p(r) N* p(r)
0 0.0147 1.47 = 1
1 0.097 9.7 =10
2 0.258 25.8 =26
3 0.342 34.2 =34
4 0.226 22.6 =23
5 0.060 6 =6
Total = 100

Homework
1) 5 unbiased coins are tossed and the number of heads are noted .The experiment
is repeated 64 times and the following distribution is obtained
No. of heads: 0 1 2 3 4 5
Frequencies: 3 6 24 26 4 1
Fit a binomial distribution and calculate theoretical frequencies
2) The following data are the no. of seeds germinating out of 10
on a damp filter paper for 80 sets of seeds. Fit a binomial
distribution to the observed data.
x: 0 1 2 3 4 5 6 7 8 9 10
f: 6 20 28 12 8 6 0 0 0 0 0
3) Fit a binomial distribution to the following data
x: 0 1 2 3 4 5
f : 2 14 20 34 22 8 Compare the theoretical frequency
with the actual frequency.

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

POISSON DISTRIBUTION

If the parameters n&p of a binomial distribution are known then we can find the
distribution.But when n is large and p is very small the application of binomial
distribution is very difficult.
Let x be any discrete random variable which can take values 0,1,2,3.. such
that the probability distribution function of x , P(x)=e - x
x!
where is a positive constant , np = . This distribution is called
the poisson distribution.
Eg: 1) Number of printing mistakes on each page of a book
published by a good publisher
2) Number of telephone calls arriving at a telephone switch
board per minute.

The poisson distribution as a limiting case of Binomial distribution

RESULT
Binomial distribution tends to a poisson distribution when n
and p 0 such that np = is finite
Proof
Probability distribution of a binomial distribution is
P ( X ) = nCx p x q n x
But = np
p= /n
q=1p
=1-/n

p( x) = nCx ( / n)x ( 1 - / n )n-x


= n(n-1)(n-2)[n-(x-1)](n-x)! x ( 1 - / n )n
x!(n-x)! nx ( 1 - / n ) x
= x n (n-1) ( n-2)(n-3) [n-(x-1)] ( 1 - / n )n
x! nx (1-/n)x

= x n (n-1) (n-2). [n-(x-1)] ( 1 - / n )n


x! n n n n (1-/n)x
= x ( 1-1/n) (1 2/n) ..( 1 (x-1)/n) [( 1 - /n) n/ ] -
x! (1-/n)x
= e - x
x!

( since as n each of the (x-1) factors (1-1/n), (1-2/n) 1- (x-1) /n 1 and


since Lt ( 1 + 1/x) x = e)
n

Result


For a poisson distribution p(x) = 1
x=0

Proof
For a poisson distribution p(x) = e - x
x=0 x!

= e - 0 + e - 1 + e - 2 + e - 3 + . .
0! 1! 2! 3!

= e [ 1 + /1! +/2!+..]
= e e
=1
Mean and variance of the poisson distribution
Mean = = x p(x)
p(x)

But for the poisson distribution p(x) = 1


Mean = = x p(x)
= x e - x
x!
= e = e x
- x

(x-1)! (x-1)!
= e ( + /2!+ 3/3!+ )
- 2
= e- e =
Mean = =

Variance = 2 = x 2 p(x) 2
p(x)
But for the Poisson distribution p(x) = 1

2 = x 2 p(x) 2
=( x(x-1) +x(e- x - 2
x!
= e + x e - x - 2
- x

(x-2 )! x!

= e- ( + 2 / 1!+ 3 / 2! +..) + 2
= 2 + 2 =
Variance = 2 =

Problems
1) A poisson variate x such that p(x = 1) = 2 Px =2). Find p(x = 0).

p(x = 1) = 2 Px =2).
e 1 = e 2

1! 2!
ie, = 1
p(x = 0) = e-110 = 1/e
0!
2)A Car-hire firm has two cars it hires out daily. The number of demands for a car on
each day is distributed as poisson variate with mean 1.5.Obtain the proportion of days
on which i) there was no demand ii) demand is refused.
Here = 1.5
p(x = 0 ) = e 1.5 1.50 =0 .2231
0!
p(x > 2 ) = 1- p(x 2) = 1- p( x = 0,1,2) = 0.1914
3) Assuming that the probability of an individual being killed in a mine
accident during a year is 1/2400. Use poisson distribution to calculate
The probability that in a mine employing 200 miners there will be atleast
one fatal accident in a year?
Here p = 1/2400 n = 200
= np = 0.083
P( x 1 ) = 1 p( x < 1) = 1 p(x = 0)
= 1 e 0.083 = 0.0796
Homework
1) In a certain factory that manufactures razor blades there is small chance
1/500 for any blade tobe defective. The blades are in packets of 10.Use
poisson distribution to calculate approximate no. of packets containing
no defective, one defective, two defective blades respectively in a
consignment of 10,000 packets.
2) If the probability of an individual suffer a bad reaction from a certain
Injection is 0.001.Determine the probability that out of 200 persons
i) exactly 3 ii) more than 2 iii) none suffer the bad reaction.

NORMAL DISTRIBUTION

This is a continuous distribution. It can be derived from the binomial distribution


as a limiting case where n The no. of trials is very large.& P the probability of
success is close to .The general equation is
f(x) = 1 e -(x-)2
2
2 where the variable x lies between - < x< , &
are called the parameters of the distribution.F(x) is called pdf of the normal
distribution N( , 2 ).The graph of the normal distribution is called the normal
curve.It is bell shaped and symmetric about its mean.The two tails of the curve extend
to +& - The curve is unimodal.The total area under the curve is 1.

Standard form of normal distribution


If X is a normal random variable with mean & standard deviation , then the
random variable Z = X- has the normal distribution with mean 0 and S.D 1.The

pdf is f(z)= 1 / 2 e z 2 / 2 , - < z< It is free from any parameters.

Area Under the normal curve


By taking z = x - the standard normal curve is formed.The total area under

this curve is divided into two parts.1) z varies from - to 0 and 2) z varies
from 0 to , each area is 0.5
1. A sample of 100 battery cells is tested to find the length of life, gave the
following results. Mean = 12 hrs. S.D. = 3 hrs.Assuming the data tobe
normally distributed what % of battery cells are expected to have life i) more
than 15 hrs.ii)less than 6hrs. Iii) between 10 & 14 hrs .

i ) when x = 15
P( x > 15) = P( X- > 15 )

= P( z > 1)
= 0.5-0.3413
= 0.1587= 16%
ii) When x = 6
P( x <6) = P( X- < 6 )

= P( z < -2)
= 0.5-0.4772
= 0.0228 = 2.28%
iii) When P( 10< x<14) = P( 10 - < X- < 6 )

= P( -0.6667 < z < 0.6667)
= 2*P(0< z < 0.6667)
= 0.2485*2=0.497 =50%
2. In a normal distribution 31% of the items are under 45and 8% are over 64.Find
the mean and S.D. Of the distribution.
Area between 0 and 45- = 0.5-0.31= 0.19

From the table 45- = -0.49

Area between 0& 64- =0.5-0.08 = 0.42

From the table 64- = 1.41


45- = -0.49 ..................(1)


64- = 1.41 .................(2)
Solving (1) & (2) we get = 50
= 10
3. In a normal distribution 7% of the items are below 35 and 11% are above
63.Find the mean and S.D. Of the distribution.
Area between 0 & 35- = 0.5-0.07= 0.43

From the table 35- = -1.48

Area between 0 & 63- = 0.5-0.11= 0.39

From the table 63- = 1.23

35- = -1.48.................(1)
63- = 1.23 .................(2)
solving(1) &(2) we get = 50 = 10.

Home work
1) X is a normal variate with mean 30 and S.D. 5.Find the probability that
a) 26<x<40
b) x-30>5
2)For a normally distributed population 7%of the items have their values less than
. 35 and 89% have their values less than 63.Find the mean and S.D..

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