0% found this document useful (0 votes)
8 views14 pages

3

Download as docx, pdf, or txt
Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1/ 14

f (x)= y 0 x (2 − x ), 0 ≤ x ≤ 2

Find the value of y 0, mean and variance of x .


(Kerala, 2005;J.N.T.U., 2003)
13. The probability density p(x ) of a continuous random variable is given by
−∨ x∨¿ ,− ∞< x<∞ ¿
p(x )= y 0 e
Prove that y 0=1 /2 . Find the mean and variance of the distribution.

{
(Calicul, 20121 ; C.S.V.T.U., 2008 ; Kuruhzhetra, 2007 )
(x+1), −1< x <1
14. If f (x)= 2
represents the density
0, of a random variable X , find E( X ) and Var ( X).
elsewhere
15. A function is defined as under:
f (x) ¿ 1/k , x 1 ≤ x ≤ x 2
¿ ¿
Find the cumulative distribution of the variate x when k satisfies the
requirements for f (x) to be a density function.

26.13 REPEATED TRIALS


1
We know that the probability of getting a head or a tail on tossing a coin is
. If the coin is tossed thrice, the probability of getting one head and two tails2
can be combined 1 H1−T − T ,1T −
1 as 3 H −T , T −T − H . The probability of each one
of these being
2
×
2
× , i.e.,
2 (2)
, their total probability shall be 3 ¿.

Similarly if a trial is repeated n times and if p is the probability of a success


and q that of a failure, then the probability of r successes and n −r failures is
given by pr q n −r .

But these r successes and n −r failures can occur in any of the n Cr ways in
each of which the probability is same.

Thus the probability of r successes is n Cr pr q n −r .


Cor. The probabilities of at least r successes in n trials
¿ the sum of the probabilities of r , r +1 , … , n successes
n r n −r n r +1 n −r −1 n n
¿ Cr p q + C r+ 1 p q +…+ C n p

26.14 (1) BINOMIAL DISTRIBUTION*


It is concerned with trials of a repetitive nature in which only the occurrence
or non-occurrence, success or failure, acceptance or rejection, yes or no of a
particular event is of interest.

If we perform a series of independent trials such that for each trial p is the
probability of a success and q that of a failure, then the probability of r
successes in a series of n trials is given by n Cr pr q n −r , where r takes any
integral value from 0 to n . The probabilities of 0 , 1 ,2 , … r , … , n successes are,
therefore, given by
n n n−1 n 2 n −2 n r n−r n
q , C1 p q , C2 p q , … , Cr p q ,…, p
The probability of the number of successes so obtained is called the binomial
distribution for the simple reason that the probabilities are the successive
terms in the expansion of the binomial ¿.
∴ the sum of the probabilities
n n n −1 n 2 n −2 n
q + C1 p q + C2 p q +…+ p =¿
(2) Constants of the binomial distribution. The mome
M 0 (t) ¿ E ( e t x ) =Σ n C x p x qn − x et x
¿ ¿
 It was discovered by a Swiss mathematician Jacob Bernoulli and was
published posthumously in 1713.
Differentiating with respect to t and putting t=0 and using (3) § 26.11, we get
the mean

μ1=n p .
Since M a (t)=e −a t M 0 (t) , the m.g.f. of the binomial distribution about its mean
(m)=n p, is given by
n n
M m (t) ¿ e
−n p t
( q + p et ) =( q e − p t + p e q t )
or
2 3 4
t t t
1+ μ1 t+ μ2+ μ 3 + μ 4 +⋯
2! 3! 4!
¿ ¿
Equating the coefficients of like powers of t on either side, we have

μ2=n p q , μ3 =n p q (q − p), μ4 =n p q[1+3(n − 2) p q].


Also
2
μ3
β 1=
3
=¿ ¿
μ2
Thus mean ¿ n p, standard deviation ¿ √ (n p q) .
skewness ¿(1− 2 p)/ √ (n p q), kurtosis ¿1β 2. 1 1
Obs. The skewness is positive for p< and negative for p> . When p= , the
skewness is zero, i.e., the probability curve of the binomial distribution2will
2 2
be symmetrical (bell-shaped).

As n the number of trials increase indefinitely, β 1 → 0, and β 2 → 3.


(3) Binomial frequency distribution. If n independent trials constitute one
experiment and this experiment be repeated N times, then the frequency of
r successes is N n Cr pr qn −r . The possible number of successes together with
these expected frequencies constitute the binomial frequency distribution.
(4) Applications of Binomial distribution. This distribution is applied to
problems concerning : (i) Number of defectives in a sample from production
line,
(ii) Estimation of reliability of systems,
(iii) Number of rounds fired from a gun hitting a target,
(iii) Radar detection.
Example 26.38. The probability that a pen manufactured by a company will
be defective is 1/10. If 12 such pens are manufactured, find the probability
that
(a) exactly two will be defective.
(b) at least two will be defective.
(c) none will be defective.
(V.T.U., 2012 S ; Burdwan, 2003)

Solution. The probability of a defective pen is 1/10=0.1


∴ The probability of a non-defective pen is 1 −0.1=0.9
(a) The probability that exactly two will be defective
12
¿ C2¿
(b) The probability that at least two will be defective
¿ 1 − (prob. that either none or one is non-defective)
¿
(c) The probability that none will be defective
12
¿ C 12 ¿
Example 26.39. In 256 sets of 12 tosses of a coin, in how many cases one can
expect 8 heads and 4 tails.
(J.N.T.U., 2003)
1 1
Solution. P ¿ head ¿= and P ¿ tail ¿=
2 2
By binomial distribution, probability8 of 84 heads and 4 tails in 12 trials is
12
P ( X=8)= C 8 ( 12 ) ( 12 ) = 812! 4!! ⋅ 21 = 4096
12
495

∴ the expected number of495


such cases in 256 sets
¿ 256 × P( X=8)=256 =30.9=31 (say)
4096
Example 26.40. In sampling a large number of parts manufactured by a
machine, the mean number of defectives in a sample of 20 is 2 . Out of 1000
such samples, how many would be expected to contain at least 3 defective
parts.
(V.T.U., 2004)

Solution. Mean number of defectives ¿ 2=n p=20 p .


∴ The probability of a defective part is p=2/20=0.1.
and the probability of a non-defective part ¿ 0.9
∴ The probability of at least three defectives in a sample of 20.
¿ 1 − (prob. that either none, or one, or two are non-defective parts)
¿
Thus the number of samples having at least three defective parts out of 1000
samples

¿ 1000 ×0.323=323
Example 26.41. The following data are the number of seeds germinating out
of 10 on damp filter paper for 80 sets of seeds. Fit a binomial distribution to
these 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

Solution. Here n=10 and N=Σ f i=80

∴ mean =
∑ f i x i = 20+56 +36+32+30 = 174 =2.175
Σfi 80 80
Now the mean of a binomial distribution ¿ n p

n p=10 p=2.175 ∴ p=0.2175 , q=1− p=0.7825


Hence the binomial distribution to be fitted is

¿
∴ the successive terms in the expansion give the expected or theoretical
frequencies which are

x: 0 1 2 3 4 5 6 7 8 9 10

19. 24. 17.


f: 6.9
1 0 8
8.6 2.9 0.7 0.1 0 0 0

RROBTIMS 265
1. Determine the binomial distribution for which mean ¿ 2 (variance) and
mean + variance ¿ 3. Also find P( X ≤ 3).
(Kerala, 2005)
2. (a) An ordinary six-faced die is thrown four times. What are the
probabilities of obtaining 4 , 3 ,2 , 1 and 0 faces ?
(b) A die is thrown five times. If getting an odd number is a success,
find the probability of getting at least four successes.
3. If the chance that one of the ten telephone lines is busy at an instant
is 0.2 .
(a) What is the chance that 5 of the lines are busy?
(b) What is the most probable number of busy lines and what is the
probability of this number?
(c) What is the probability that all the lines are busy?
(V.T.U., 2002 S)
4. If the probability that a new-born child is a male is 0.6 , find the
probability that in a family of 5 children there are exactly 3 boys.
(Kurukshetra, 2005)
5. If on an average 1 vessel in every 10 is wrecked, find the probability
that out of 5 vessels expected to arrive, at least 4 will arrive safely.
( P . probability that (i) exactly two will strike the target, (ii) at least
two will strike the target.
6. A sortie of 20 aeroplanes is sent on an operational flight. The chances
that an aeroplane fails to return is 5 %. Find the probability that (i)
one plane does not return (ii) at the most 5 planes do not return, and
(iii) what is the most probable number of returns?
7. The probability that an entering student will graduate is 0.4 .
Determine the probability that out of 5 students (a) none (b) one and
(c) at least one will graduate.
8. Out of 800 families with 5 children each, how many would you expect
to have ( a ) 3 boys, (b) 5 girls, (c) either 2 or 3 boys? Assume equal
probabilities for boys and girls.
(V.T.U., 2004)
9. If 10 per cent of the rivets produced by a machine are defective, find
the probability that out of 5 rivets chosen at random (i) none will be
defective, (ii) one will be defective, and (iii) at least two will be
defective.
(Kurukshetra, 2013)
10.In a bombing action there is 50 % chance that any bomb will strike the
target. Two direct hits are needed to destroy the target completely.
How many bombs are required to be dropped to give a 99 % chance or
better of completely destroying the target.
(V.T.U., 2003 S)
11.A product is 0.5 % defective and is packed in cartons of 100 . What
percentage contains not more than 3 defectives?
12.If in a lot of 500 solenoids 25 are defective, find the probability of
0 , 1 ,2 , 3 defective solenoids in a random sample of 20 solenoids.
13.500 articles were selected at random out of a batch containing 10,000
articles, and 30 were found to be defective. How many defectives
articles would you reasonably expect to have in the whole batch?
(J.N.T.U., 2003)
14.Fit a binomial distribution for the following data and compare the
theoretical frequencies with the actual ones :

x: 0 1 2 3 4 5

f: 2 14 20 34 22 8

(Bhopal, 2006)
16. Fit a binomial distribution to the following frequency distribution :
(a) x :10 1
(b) y : 28 62 10 4
(b) x : 0 1 2 3 4 5 6
(U.P.T.U., 2011)

f:
13 25 52 58 32 16 4

(Kuru
kshetr
a,
2009;
C.S.V.
T.U.,
2007)

26.15 (1) POISSON DISTRIBUTION*


It is a distribution related to the probabilities of events which are extremely
rare, but which have a large number of independent opportunities for
occurrence. The number of printing mistakes per page, number of accidents
on a highway, number of dishonoured cheques at a bank, number of persons
born blind per year in a large city and the number of deaths by horse kick in
an army corps are some of the phenomena, in which this law is followed.

This distribution can be derived as a limiting case of the binomial


distribution by making n very large and p very small, keeping np fixed ¿,
say).

The probability of r successes in a binomial-distribution is


n( n− 1)(n− 2)⋯(n − r +1) r n − r
P(r ) ¿ n C r p r qn − r= p q
r!
¿ ¿
As n → ∞ , p → 0(n p=m), we have
r
m
P(r )= < ¿¿
r ! n→∞
so that the probabilities of 0 , 1 ,2 … , r , … successes in a Poisson distribution
are given by
2 −m r −m
−m −m m e m e
e ,me , , ⋯, ,⋯
2! r!
The sum of these probabilities is unity as it should be.

(2) Constants of the Poisson distribution. These constants can easily be


derived from the correspon n p=m
$$
Mean ¿<(n p)=m
μ2 ¿<(n p q)=m<(q )=m
$$
∴ Standard deviation ¿ √ m
(V.T.U., 2014)

Also μ3=m, μ4 =m+ 3 m2


∴ Skewness ( ¿ √ β 1 )=1 /m , Kurtosis ( ¿ β 2 )=3+ 1/m.
Since μ3 is positive, Poisson distribution is positively skewed and since β 2> 3,
it is Leptokurtic.
(3) Applications of Poisson distribution. This distribution is applied to
problems concerning : (i) Arrival pattern of 'defective vehicles in a
workshop', 'patients in a hospital' or 'telephone calls'.
(ii) Demand pattern for certain spare parts.
(iii) Number of fragments from a shell hitting a target.
(iv) Spatial distribution of bomb hits.

Example 26.42. If the probability of a bad reaction from a certain injection is


0.001 , determine the chance that out of 2,000 individuals more than two
will get a bad reaction. (V.T.U., 2008; Kottayam, 2005)

Solution. It follows a Poisson distribution as the probability of occurrence is


very small.
Mean m=n p=2000(0.001)=2
Probability that more than 2 will get a bad reaction
¿ 1 −¿ prob. that no one gets a bad reaction + prob. that one gets a bad
reaction + prob. that two get bad reaction]

¿
Example 26.43. In a certain factory turning out razor blades, there is a small
chance of 0.002 for any blade to be defective. The blades are supplied in
packets of 10, use Poisson distribution to calculate the approximate number
of packets containing no defective, one defective and two defective blades
respectively in a consignment of 10,000 packets.
(Kurukshetra, 2009 S; Madras, 2006 ; V.T.U., 2004)
Solution. We know that m=n p=10× 0.002=0.02
−0.02
e =1 − 0.02+ ¿ ¿
Probability of no defective blade is e −m =e −0.02=0.9802
∴ no. of packets containing no defective blade is

10 , 000 ×0.9802=9802
Similarly the number of packets containing one defective blade
−m
¿ 10 , 000 ×m e
¿ 10 , 000 ×(0.02)×0.9802=196
Finally the number of packets containing two defective blades
2 −m
m e
¿ 10 , 000 × =10 , 000 ׿ ¿
2!
Example 26.44. Fit a Poisson distribution to the set of observations:

x: 0 1 2 3 4

f: 122 60 15 2 1
(U.T.U., 2010; Bhopal, 2007 S; V.T.U., 2004)
Σ f i xi 60+36+6+ 4
Solution. Mean ¿ = =0.5.
∴ mean of PoissonΣdistribution
fi 200i.e., m=0.5 .
Hence the theoretical frequency for r successes is
−m
Ne ¿¿
∴ the theoretical frequencies are

e th ca 2 3 4

x: 0 1 15 2 0 ( ∵ e −.5 =0.61 )
f : 121 61 15

PROBLEMS 26.6
1. If a random variable has a Poisson distribution such that P(1)=P(2),
find
(V.T.U., 2003)
(i) mean of the distribution. (Rohtak, 2011 S ) (ii) P(4). is two-thirds
of the probability that X =1. Find
2. X is a Poisson variable and it is found that the probability that X =2 is
two-thirds of the X exceeds 3 ?
the probability that X =0 and the probability that X =3. What is the
probability that X .

3. A certain screw making machine produces on average of 2 defective


screws out of 100 , and packs them in boxes of
4. A 500 . Find the probability that a box contains 15 defective screws.
(Kurukshetra, 2006)
5. Using Poisson distribution, find the probability that all of the spades
will be drawn from a pack of well-shuffled cards atleast once in 104
consecutive trials. (Given e −2=0.136 ).
(U.T.U., 2011)
6. A manufacturer knows that the condensers he makes contain on the
average 1 % defectives. He packs them in boxes of 100 . What is the
probability that a box picked at random will contain 3 or more faulty
condensers?
7. A car-hire firm has two cars which it hires out day by day. The number
of demands for a car on each day is distributed as a Poisson
distribution with mean 1.5. Calculate the proportion of days ( i ) on
which there is no demand, (ii) on which demand is refused. (
−1.5
e =0.2231 ).
(Bhopal, 2008 S ; J.N.T.U., 2003)
8. The incidence of occupational disease in an industry is such that the
workmen have a 10 % chance of suffering from it. What is probability
that in a group of 7 , five or more will suffer from it?
9. The frequency of accidents per shift in a factory is as shown in the
following table:
Accidents per shift : 0 1 2 3 4
Frequency Calculate
Frequency : the
180mean
92 number
24 3 1of accidents per shift and the
corresponding Poisson distribution and compare with actual
observations.
10.A source of liquid is known to contain bacteria with the mean number
of bacteria per cubic centimetre equal to 3 . Ten 1 c.c., test-tubes are
filled with the liquid. Assuming that Poisson distribution is applicable,
calculate the probability that all the test-tubes will show growth i.e.,
contain atleast 1 bacterium each.
11.Find the expectation of the function ϕ (x )=x e− x in a Poisson
distribution.
(V.T.U., 2003)
[Hint : If m be the mean of the Poisson distribution, then expectation
of ∞ x −m
o(x )⋅m e
o (x)=∑ =m exp . m ( e−1 −m −1 )
x=0 x!
12.Fit a Poisson distribution to the following :

x: 0 1 2 3 4

(Rohtak
, 2011;
Bhopal,
f: 46 38 22 9 1
2008;
V.T.U.,
2003 S)

13.Fit a Poisson distribution to the following data given the number of


yeast cells per square for 400 squares :

No.
of
cell
s 0 1 2 3 4 5 6 7 8 9 10
per
sq.
:

No.
of
10 14
squ : 3 3
98 42 8 4 2 0 0 0
are
s
(C.S.V.T.U., 2007)

26.16 (1) NORMAL DISTRIBUTION*


Now we consider a continuous distribution of fundamental importance,
namely the normal distribution. Any quantity whose variation depends on
random causes is distributed according to the normal law. Its importance
lies in the fact that a large number of distributions approximate to the
normal distribution and as such it is a corner stone of modern statistics.
x−n p
Let us define a variate z=
√(n with
where x is a binomial variate p q) mean n p and S.D. (n p q) so that z is a

variate with mean zero and variance unity. In the limit as n tends to infinity,
the distribution of z becomes a continuous distribution extending from − ∞ to
∞.
It can be shown that the limiting form of the binomial distribution (1) for
large values of n when neither p nor q is very small, is the normal
distribution. The normal curve is of the form
1 −¿¿
y= e
σ √ (2 π )
¿
where μ and σ are the mean and standard deviation respectively.
(2) Properties of the normal distribution
I. The normal curve (2) is bell-shaped and is symmetrical about its mean. It
is unimodal with ordinates decreasing rapidly on both sides of the mean
(Fig. 26.3). The maximum ordinate is 1/σ √ (2 π ), found by putting x=μ in (2).

As it is symmetrical, its mean, median and mode are the same. Its points of
inflexion (found by putting d 2 y /d x 2=0 and verifying that at these points
3 3
d y /d x ≠ 0 ) are given by x=μ ± σ , i.e., these points are equidistant from the
mean on either side.
II. Mean deviation from the mean μ

¿
(Rohtak, 2011 S)
III. Moments about the mean

μ2 n+1 ¿

Thus all odd order moments about the mean vanish.

μ2 n ¿

Repeated application of this reduction formula, gives


2n
μ2 n=(2 n− 1)(2n − 3)… 3 ⋅1 σ
In particular, μ2=σ 2 , μ 4=3 σ 4.
Hence
2
μ3 μ4
β 1= 3
=0 and β2= 2
=3
μ2 μ2
i.e., the coefficient of skewness is zero (i.c, the curvo in mymmotrical) and
the Kurtosis is 3. This is the basis for the choice of the value 3 in the
definitions of platykurtic and loptokurtic (page 844).
IV. The probability of x lying between x 1 and x 2 in givon by tho area under
the normal curve from x 1 to x 2, i.e., P ( x 1 ≤ x ≤ x 2)

¿
The values of each of the above integrals can be found from the table IV- Λ
ppendix 2 , which gives the values of
z
1
∫ e− z / 2 d z
2

P(z )=
√ (2 π ) 0
for various values of z . This integral is called the probability integral or the
error function due to its use in the theory of sampling and the theory of
errors.

Using this table, we see that the area under the normal curve from z=0 to
z=1, i.e. from x=μ to μ+σ is 0.3413.
∴ (i) The area under the normal curve between the ordinates x=μ − σ and
x=μ+ σ is 0.6826 , ∼ 68 % nearly. Thus approximately 213 of the values lie
within these limits.
(ii) The area under the normal curve between1 x=μ −2 σ and x=μ+2 σ is
0.9544 ∼ 95.5 %, which implies that about 4 % of the values lie outside these
limits. 2
(ii) 99.73 % of the values lie between x=μ −3 σ and x=¿ μ+3 σ i.e., only a
quarter % of the whole lies outside these limits.
(iv) 9.5 % of the values lie between x=μ −1.96 σ and x=¿ μ+1.96 σ i.e., only 5 %
of the values lie outside these limits.
(v) 99 % of the values lie between x=μ −2.58 σ and x=¿ μ+2.58 σ i.e., only 1 %
of the values lie outside these limits.
(vi) 99.9 % of the values lie between x=μ −3.29 σ and x=μ+3.29 σ .

In other words, a value that deviates more than σ from μ occurs about once
in 3 trials. A value that deviates more than 2 σ or 3 σ from μ occurs about
once in 20 or 400 trials. Almost all values lie within 3 σ of the mean.

Fig. 26.4

The shape of the standardised normal curve is


1 2
−z /2
y= e where z=(x − μ)/σ
√(2 π )
(3)
and the respective areas are shown in Fig. 26.4. ' z ' is called a normal
variate. Areas under the Normal curve are given in Table IV.

Obs. 50 % area lies in the z -interval (− 0.745 ,0.745) and 99 % area lies in the z -
interval (− 2.58 ,2.58).
(3) Normal frequency distribution. We can fit a normal curve to any
distribution. If N be the total frequency, μ the mean and σ the standard
deviation of the given distribution then the curve
N −¿¿
y= e
σ √ (2 π )
¿
will fit the given distribution as best as the data will permit. The frequency
of the variate between x 1 and x 2 as given by the fitted curve, will be the area
under (1) from x 1 to x 2.
(4) Applications of normal distribution. This distribution is applied to
problems concerning:
(i) Calculation of errors made by chance in experimental measurements.
(ii) Computation of hit probability of a shot.
(iii) Statistical inference in almost every branch of science.

26.17 PROBABLE ERROR


Any lot of articles manufactured to certain specifications is subject to small
errors. In fact, measurement of any physical quantity shows slight error. In
general, these errors of manufacture or experiment are of random nature
and therefore, follow a normal distribution. While quoting a specification of
an experimental result, we usually mention the probable error ( λ ). It is
such that the probability of an error falling within the limits μ − λ and μ+ λ is
exactly equal to the chance of an error falling outside
1 these limits, i.e. the
chance of an error lying within μ − λ and μ+ λ is .
μ+ λ 2
1
∴ ∫e
σ √λ/(2σ π ) μ − λ
−¿¿

1 1

2
− z /2
e d z=
√(2 π ) 0 x − μ 4
z=
[ σ ]
The table V , (Appendix 2) gives λ /σ=0.6745 2
Hence the probable error1λ=0.6745 σ 2∼ σ . 4
Obs. Quartile deviation ¿ ( Q3 −Q 1 ) ∼ σ3; Mean deviation ≈ σ
[p. 839] 2 3 5
∴ Q.D. : M.D. : S.D. =10 :12: 15.
(U . P . T . U .,2009)
Example 26.45. X is a normal variate with mean 30 and S.D. ., find the
probabilities that (i) 26 ≤ X ≤ 40,
(ii) X ≥ 45 and (iii) ¿ X −30∨¿ 5.
(J.N.T.U., 2005)

Solution. We have μ=30 and σ =5


X − μ X −30
∴ z= =
σ 5
(i) When X =26 , z=−0.8 ; when X =40 , z=2
∴ P(26 ≤ X ≤ 40)=P(− 0.8 ≤ z ≤2)
¿ P(− 0.8 ≤ z ≤0)+ P(0≤ z ≤2)
¿ P(0 ≤ z ≤0.8)+0.4772 =45 , z=3 ¿
¿ 0.2881+0.4772=0.7653
[Using Table IV] ¿
(ii) When

P( X ≥ 45)=P (z ≥ 3)=0.5 − P(0 ≤ z ≤3)
¿ 0.5 − 0.4986=0.0014
(iii) P[¿ X −30∨≤5 ]=P[25 ≤ X ≤35]

¿ P(− 1≤ z ≤ 1)=2 P (0 ≤ z ≤1)


¿ 2 ×0.3413=0.6826
∴ P[¿ X −30∨¿5 ]=1 − P[¿ X −30∨≤ 5]

¿ 1 −0.6826=0.3174 .
Example 26.46. A certain number of articles manufactured in one batch
were classified into three categories according to a paiticular characteristic,
being less than 50, between 50 and 60 and greater than 60 . If this
characteristic is known to be normally distributed, determine the mean and
standard deviation for this batch if 60 % ,35 % and 5 % were found in these
categories.

Solution. Let μ be the mean (at z=0 ) and σ the standard deviation of the
normal curve (Fig. 26.5).
Now 60 % of the articles have the characteristic below 50 , 35 % between 50
and 60 and only 5 % greater than 60.

Let the area to the left of the ordinate P Q be 60 % and that between the
ordinates P Q and S T be 35 % so that the areas to the left of P Q ( z =z1 ) and
S T ( z=z 2 ) are 0.6 and 0.95 respectively, i.e., the area O P Q R=0.6 − 0.5=0.1
and the area O S T R=0.45 . 50 − μ
((
∴ area corresponding to z 1 ¿ 60− μ=0.1
and that corresponding to z 2 ¿ σ
))
=0.45
From the table IV, we have σ
(50 − μ)/ σ ¿ 0.2533 ¿ and (60 − μ)/ σ=1.645
σ ¿ 7.543 ¿ and μ=48.092.
whence

Fig. 26.5

Example 26.47. In a normal distribution, 31 % of the items are under 45 and


8 % are over 64. Find the mean and S.D. of the distribution.
(M.T.U., 2013 ; V.T.U., 2012 S ; C.S.V.T.U., 2008)

Solution. Let x́ be the mean


When x=45 ,and σ the
let z=z S.D. 31 % 45
1 so that z 1=
of−the
x́ items are under 45
means area to the left of the ordinate x=45. (Fig. σ26.6)
(i)
z1 0 0
∴ ∫ ϕ(z )d z=0.31 or ∫ ϕ( z)d z −∫ ϕ (z)d z=0.31
Hence −∞ −∞ z1
0 0
(i)
∫ ϕ ( z )d z= ∫ ϕ ( z)d z − 0.31=0.5 −0.31=0.19
z1 −∞
From table IV, z 1=− 0.5
When x=64 , let z=z 2 so that z 2=( 64 − x́ )/σ
∴ ∫ ∞z ϕ (z)d z=0.08 or ∫ ∞0 ϕ ( z) d z − ∫ 0z ϕ(z )d z=0.08
2
2

Hence z 2 ∞

∫ ϕ ( z )d z=∫ ϕ (z)d z − 0.08=0.5 − 0.08=0.42


0 0
(iv)
From table IV, z 2=1.4
From (i) and (ii), 45 − x́=−0.5 σ
From (iii) and (iv), 64 − x́=1.4 σ
Solving these equations, we get x́=50 and σ =10.
Example 26.48. In a test on 2000 electric bulbs, it was found that the life of
a particuiar make, was normally distributed with an average life of 2040
hours and S.D. of 60 hours. Estimate the number of bulbs likely to burn for
(a) more than 2150 hours,
(b) less than 1950 hours and
(c) more than 1920 hours and but less than 2160 hours.
(Bhopal, 2008 S ; U.P.T.U., 2008)
Solution. Here μ=2040 hours and σ =60 hours.
(a) For x=2150 ,
x−μ
z= =1.833
σ

o It was discovered in 1837 by a French mathematician Simon


Denius Poisson (1781 - 1840).
o In 1924, Karl Pearson found this distribution which Abraham
De Moivre had discovered as early as 1733 . It is also known as
Gaussian distribution due to Karl Friedrich Gauss. See footnote
p. 843, 647 and 37.

You might also like