of.

ExAMPLE17
probability
ind the probability
Find the of getting atleo
east
sinultaneousty.

thrown

10 coins are
heads
SOLUTION

=
10, p =q =5
Given, n
successes)
=
P(x)=n e,p*q"-*
p(getting x
p(X27)
p(getting atleast7heads) +p(10)
p(X27)= p(7) +p(8) tp(9)

PX27) = 10c (Y +10«{åJ J+10,(

(
+10 Co 10
10
+10c +10c
10-10
10 C7
+ 10 co + 10 col
=
7i0 [10c+ 10 cg
176
10 [120+45 10+1]
+ =
0210
p(X27) = 0.171875

EXAMPLE 18
screws produce
is known to 5% defective. In o
A machine manufacturing
sample of 15 screws, what is the probability that there are () exacl
random
three defectives, (i) not more than three defectives
IO8
950LUTON Applied Probability and
OSOLU UTION

5 Statistics
5%oo = 0.05
G i v e n ,

=1-p -0.05 0.95

= 0.95
= 15
Exactlythree defectives
ly ththree defe
xactly
defectives) =

p(X= 3) nc^p? =

15 c3 (0.05)* (0.95)15-3 qn-3.

15
15xx 14x 13
14x1
1x2x3 (0.000125) (0.54036)
pX=3) 0.0307
Not
more than three defectives
(ti)
(not
more

pXS 3) =
than 3
defectives)=p(X s3
p(0)+p(1) + p(2) +p(3)
=
15 co (0.05)° (0.95)15 + 15 c, (0.05)1 (0.95)14
+15c (0.05)? (0.95)13 +15 c (0.053 (0.95)12
0.4632+0.3657 +0.1347+0,030733
PXS3) 0.994
S 5 POISSONDISTRIBUTION

DEFINITION
limiting of binomial distri
Poisson distribution is
a case

following assumptions.

() The number oftrails "n' should be indefinitely large, (i.e) n »

(i) The probability ofsuccusses 'p' for each trial is indefinitely small

(ii) n p =), should be finite, where Ais a constant,

DERIVATION OF THE PROBABILITY FUNCTION OF THE POISSON DISTRIBUTION

We know that, the binomial distribution is given by,
PXx) =
n c,p* q"-
n!
(1-p)r-x
n-x)!x! P*
1.2.3.(n-x)...n (1-p)
1.2.3 (n -x)x! 1-p

nn(n-1)(n-2)...(n-xt)|Nn_1-An
(1-Am
x! 1-Nn)
 Neu

n -2)..-X+ )* Probabiüity and Statistics

1
(1-Nny -Nn
n(n-1)(-2...nX+1) A
n
1
n
X=x) |n -x

.1)
Lt n-x
Weknow that,
nco 1 e-A
Lt Lt
Alnd

n-0ol1. no
Ae-a
when n co, the R.H.S of (1), gives
.(2)
Substituting (2) in (1), we get,

pX=x) = x e- x0,1,2,.
Poisson
Hence the probability function of a random variable 'X' which follows
distribution and it is given by,
POX-)- x!
x =0,1,2,... ,
o
)
lo otherwise
Ramdom Variables
1.117
MOMENT GENERATING FUNCTION OF THE
POISSON DISTRIBUTION
We know that, the
m.g.f. of arandom variable "X' is given by,
0

Mx) =
X e" p(x)

e
0
x!

e- e

e-1+Ae+ te,1
e-.el e
Mx(/) = eMet-1)

MEAN AND VARIANCE OF THE

POISsON DISTRIBUTION
We know that, for discrete probability distribution, mean is given by,

HECX) 2xp*) =0

= 0
x!

x!

= e.E1
x 0
x!

Ae-a
-1)!

e 1+A+ .
Hence, the mean ofthe Poisson distribution is A.
Now, H2-ECX)
 2

Applied Probability and Statistics

1.118

x!
e-Ar
-

r
{x(rx(r--1) +x}
= 0
x!

-1) e-A A + e-AA

r = 0
x! x = 0
x!

xx-1)e-AN-22 tA
x =
0 *( 1)(r-2)... 1
-

-2
- 2 (r-2)! 0, when' 'n'is negative
A2
=e- A2| 1+ +2 . +A

- etA-A A2 +Aa
2 2+a
Variance, H2 Hh -(4, =
2+A-0)P =
*+A-A =
A
Variance, H =A |

RESULT
Mean Variance=A
 Applied Probability
ePLES and
Poisson variate such that Statistics
a p(X 1)==

a n dip(X=3).
p T0 and
pX 2)
OSOLUTION =ind
P =x) = e
. X =1) = e - l ) =

p(X=2) =
-
.(2)
e-
()
3
2
4

(4 102 *1-
Tofindp(X=0)
pX=0) = 1 0
0! e-

PX 0) eT
=

Tofind p(X=3)
e-A 3
PCX=3) = 3! 6

3
p(X=3) = 6

EXAMPLE 7 defective. he
of hisproduct isthan pinsf will
cotter pins knows
that 5%
nanufacturer of
guarantees that not more 10
and to meet the
pins in bores of100 bax will fail
r probabiliy that
approximate
a

P ve.HWhat is the
3uaranteed quuality?
 Random Variables 1.125
SOLUTION
= 0.05
Given, n= 100, p =5o 100
Mean, A =
np
=
100 x 0.05 =
5 =FA

The Poisson distribution is,p(X =x) =

-A 5]
x

= 5
x!
To find the approximate probability that a box will fair to meet the guaranteed
quality
pX> 10)= 1 -p(X< 10)
1-p(0) +p(1) +... +p(10)]
e s 53
e-550 e-55 e-5 52
-1 0! 1! 2! 3!
e5S es 56e-557 e-s 58
5! 7! 8!
e-5 59 + es 510
9! 10!

= 1-e-s 510

1-e-s [146.36] = 1-0.9863 0.014

 6 EOMETRICDISTRIBUTION
DEFINITION
A random variable 'A-1s said to follow
l non-negative values and its Geometric distribution, if it assumes
probability mass function (p.m.f) is given by,
PXx) =

q;p; x=0, 1,2,..., 0<p

s1, where q =1-p
NOTE
Putting x= 0, 1, 2, ..,
we will get qop, qp, q2p, which are the various
terms
terms of geometric ...,
progression. Hence it is known as geometric
distribution. geometric
4: We can also take the
p.m.f. of the geometric distribution as,
X=x)=q*~lp;x= =1,2,... 0<p <1, where q l-p
MoMENT GENERATION FUNCTION (MGF) OF GEOMETRIC
DISTRIBUTION
The Moment Generation Function is given by,
Mx()= E(e)
r
et p()
= 0 px)= 9 P
Random Variables
1.137

p 2(e' qy
0

p[l +q el +(q e'?+...]

p - q e'l ((1-x)- =
1 +x +x?..|
P
Mx) (1-g e')
MEAN AND VARIANCE OF A GEOMETRIC DISTRIBUTION

My) (1-q e')

Mean E(X) =
M, (0)
M) -qer?
M,(0) (1-q
M,(0) 24
p
Mean = 2

ECX) M,0)
M)pa -2e'(1-qe)-g e)+e' (1-q e'
(1-qe'
M.)= p ed-ge)-qe)+e0(1-qe®p
(1-q eo
pg E)+(1-g 1 (-9) P
1-4
pg2-2g2:|
p9 Pt-1

p 92q1-g)+p:
p

p 424pp2
p
1.138

=p9 pl24+p)
p
- pg 2qtp

p9 p +q=1
+1
-pp
M0) g1+g)
p
Var(X) E(X?)- [E(X)]2
p 2( 1 + g ) - / 2 }

Var(X)
p2
 EXAMPLE 2
Speciance.al rice Jollowin,
Let one copy of a magazine out of 10 copies bears a special n
geometric random distribution. Determine its mean andvariance.
SOLUTION

Given,

To find mean, Mean =

2
P 7 =9
To find variance
Variance = 2
90

ExAMPLE 3
Suppose that a trainee soldier shoots a target in an independent fashin.
probability that the target is shot on any one shot is 0.8 shion. Ifthe
What is the probability that the target would be
hit on 6" attempt
(ii) What is the probability that it takes him less than 5 shots.
(ii) What is the probability that it takes him an even number ofshots,

SOLUTION
p 0.8, q=1-p = 1-0.8 0.2
The geometric distribution is given by,
pX=x) = q*-lp, x= 1,2, ..
To find the probability that the target would be hit on 6 attempt
p(the target would be hit on 6 attempt) p(X=6)
=

p(X=6) (0.2)6-1 (0.8)

=

= (0.2 (0.8)
pX=6) = 0.000256

Gi) To find the probability that it takes him less than 5 shots
p(it takes him less than 5 shots) =p(X <5)
p(X <5) p(X= 1) +p(X =2)
+p(X=3) +p(X =4)
(0.2)-1 (0.8) + (0.2)2-1 (0.8) + (0.2)3-1 (0.8) + (0.2)4- (0
(0.2)9(0.8) +(0.2) (0.8) + (0.2) (0.8) +(0.2}" (0.3)
1.140 Applied Probability and Statistics
=
0.8+ (0.2) (0.8) +
(0.2) (0.8) +(0.2)" (0.8)
pX <5) =
0.9984
(ii) To find the probability that it takes him an even number of shots
p(taking him an even no of shots) =p(X =2) +p(X=4) +pX= 6)
+

=
(0.2)2-1 (0.8) + (0.2)4-1 (0.8) + (0.2)6-1(0.8) + ...

(0.2)! (0.8) +(0.2)3 (0.8) + (0.2)5 (0.8)+.

=

(0.2) (0.8) [1 +(0.2) (0.8) + (0.2 (0.8) + ...]

=

0.16 [1+ (0.04) +(0.04)2 + ...]

=
0.16 [1-0.04]-1 [(1-x)-l =1 +x +x2 +...]
0.16(0.96) 0.1536
= =
 AS

DEFINITION
random variable Xis said tofollow an exponential distribution
A continuous
probability density function is given by,
with parameter, A> 0, ifits
Ae-x, x20
f)= 0 otherwise
Moment Generating Function (MGF) of Exponential Distribution.
Moment Generating Function

Mx0)e"ft)dx
0
CO

elx et e-Ax dx
0
1.156 Applied Prohability amd Statistics

A.e-3)x dx
0

el-x1
A-)Jo e--1)x

--)
e 0 ,e0 = 1|
- a- le
A
--)10-1]

--
. Dividing both numerator

0 denominator by A]
1-

(1-tn)
2
Mg)=1+

= - E(X)
NOw,

Coefficient ofinMy )

, r=1,2,.. (A)

Sibr 1 in (AA) Mean

 Random Variables
1.157
Subr 2 in (A)

Variance H-(4

-
Variancee
EXAMPLE 1
Suppose the duration 'X' in minutes of long distance calls from your home,
follows exponential law with p.df

Sc)
0, otherwise
find () pX> 5), (2) p(3 SXS6), Mean of Xand Variance ofX.
SOLUTION
(1) To find p(X> 5)

pOX> 5) =

sa)dx

Je-5 dx

e-/5 dx

e-

0-e
- 1 5

xe-lxe
P(X> 5) e
 Applied Probability and Statistics
1.158
sX ss6)
(2) Tofind p(3 6

p(3Xs6) Sx)dr
3

e-x/5 dx
3
6

e-x/5 dx
3

e-r/s
6

3L-1/5
e-65-e-3/5]
P(3SXS6) = e-3/5-e-65

To find Mean and Variance ofX

Mean 5

1
(5)2 = 25
Variance 2
=