beximp) =(%) pr a-pyr*= (2) (725) a -n"
cel
_n(n=1) (1-2)... (n= +1) (
ane.
lim b (x; 1, p) = [From (“*)]
re
Definition. A random variable X is said to follow a Poisson distribution if it assumes
only non-negative values and its probability mass function is given by :
eA
p(x,r)=P(X=x)=) x!
0, otherwise
oan eles 2reemmt fave 0) as (8-15)
Here A is known as the parameter of the distribution. We shall use the notation
X ~ P(A), to denote that X is a Poisson variate with parameter a.
Remarks 1. It should be noted that YP (X=x)=e# D M/x!=e%e* =1
- 0
2. The corresponding distribution function is :
F(x)=PXsx)=L p()=e* & M/r;x=0,1,2,...
= -
3, Poisson distribution occurs when there are events which do not occur as outcomes of a
definite number of trials (unlike that in binomial distribution) of an experiment but which occur
at random points of time and space wherein our interest lies only in the number of occurrences
of the event, not in its non-occurrences.
4, Following are some instances where Poisson distribution may be successfully employed :
() Number of deaths from a disease (not in the form of an epidemic) such as heart attack
or cancer or due to snake bite,
(i) Number of suicides reported in a particular city.
(ii) The number of defective material in a packing manufactured by a good concern.
(iv) Number of faulty blades in a packet of 100.
(2) Number of air accidents in some unit of time.
(vi) Number of printing mistakes at each page of the book.
(vii) Number of telephone calls received at a particular telephone exchange in some unit
__ of time or connections to wrong numbers in a telephone exchange.
(citi) Number of cars passing a crossing per minute during the busy hours of a day.
(ix) The number of fragments received by a surface area ‘A’ from a fragment atom bomb.
(x) The emission of radioactive (alpha)particles. :
ft pets The Poisson Process. The Poisson distribution may also be obtained
ndependently (i.e., without considering it as a limiting form of the binomial
distribution) as follows :Poisson DistRIBUTION
64.1 POISSON DISTRIBUTION
Poisson distribution is a particular limiting form of the Binomial distribution when p (or g)
is very small and 7 is large enough.
Poisson distribution is
P(r)= a
where m is the mean of the distribution.
Proof. In Binomial distribution.
PUY Cee
=C,(-pyr
:
:
a ele) (2) (aiseontant)
un (n=1) (n=2)..(n=r=1) e ( = c
sete]
lin( 1-2
oeUS reall aes -{uetetete ras
(r-))! Wa 3! 4! rt
Safle e+] 2 e2ep,
e Renee
MOMENT GENERATING FUNCTION OF POISSON DISTRIBUTION
(A.M.LE., Summer 2000)
e"m
r!
Let M(0) be the moment generating function, then
RU gk er [teme og md
rt 2! 3L
Solution. PO)=
ean
M.O= Qe res
34,6 CUMULANTS
The cumulant generating function K,(0) is given by .
m gm = ont-d)
K,(0)=log, M, (1) = log, e"“? = m(e' -1) log, €
anti & Ein fa gt rh
= me ~dam[rere Sake ae | te nfs Ste
3! r!
Now K,=rth cumulant = coefficient of & in K()=m
7
k=m, where r=1,2,3,.
Hence, all the cumulants of the Poisson distribution are equal. In particular, we have
Mean = , Hy = K, =m
hy =K, + 3K2 =m +3ne
2 a?
hm
Bieta, =) Pa oe
Byrom By
.7 RECURRENCE FORMULA FOR POISSON DISTRIBUTION
Solution. By Poisson distribution
p= ~(l)
om
BORD) ey ~-Q)
By dividing (2) by (1), we get
P(r+l)_e"m'™
Pr) (rtDle
de Ans.
Pr +=— PO)
i the Poisson distribution is 2, find the probabilities for
one ion 25 iiss ‘vecurrence relation of the Poisson distribution, Also find
[Recurrence relation]Higher Engineering Mathematics il
1678
2
Now P(r +t) =—— Pr) (m=2) |
r+t
2 2
ec = ——P(0) = (0.1353) = 0.2706 eRe gai
If js pe Om gage 1353) P(O)=e™=e?= 0.1353
2
If or=1, PQ=— PW) =2(0.2706) = 0.2706
141 2
2 2
= = P(2 == (0.2706) = 0.1804
if 12 eFiG) = aoe) 302 )
2 1
= — PQ) ==(0. = 0.0902
It Ones eae 3 (0.1804)
P(r 24)=P (4) + PS) + PO).
1-[P. (0) + P(1)+PQ)+P GB)
1- [0.1353 + 0.2706 + 0.2706 + 0.1804]
= 10.8569 = 0.1431 Ans,
Example 2. Assume that the probability of an individual coal miner being killed in a mine
1
accident during a year is F455. Use appropriate statistical distribution to
calculate the probability that ina mine employing 200 miners, there will be at
least one fatal accident in a year. (A.MLE.TE., Summer 2001)
1
=—, n=200
Solution, a0
ae
SA za a2
P (Atleast one) = P(1 or2 or 3 or ..... or 200) =P (1) + P(2)+P (3) +...+ P (200)
para
2 ae eye
= 1 PQ)=1-—— = 1-28 =1-0.92 = 0.08
ixample3. Suppose 3% of bolts made by a machine are defective, the defects occurring a:
random during production. If bolts are packaged 50 per box, find
(a) exact probability and
(b) Poisson approximation to it, that a given box will contain 5 defectives. |
Ans
Solution.
(a) qz=1-p=1-0.03 = 0.97
Hence the probability for 5 defective bolts in a lot of 50
= C, (0.03)' (0.97) = 0.013074 (Binomial Distribution)
3053
(6) To get Poisson approximation m =n p= 50x 75 = 3-15
rte ned
Required Poisson approximation = a ee = 0.01412 Ans.
Example 4, The number of arrivals of customers during any day follows Poisson distribution
with a mean of 5. What is the probability that the total number of customers 0"
two days selected at random is less than 2?
Solution. m=5
Pw)= ae Pr) pes