PROBABILITY

Certainty and uncertainty:There are some cases that can happen surely in the
daily life. For example Friday certainly comes after Thursday. A night comes after
evening A man dies sooner or later after birth. These are the cases for certainty.

Some cases may arise that under certain condition more than one result are
possible and occurrence of a particular result is unpredictable and remains
uncertain.for examples, after tossing a fair coin a result may be either head or tail.
If we roll a dice having 6 faces 1, 2, 3, 4, 5, 6; it is not certain that which face is
going to be occurred. These are the cases of uncertainty.

A numerical measure of such an uncertainty is known as probability.The synonyms

of word probability are possibility or chance or probable etc.

SOME BASIC TERMS UNDER PROBABILITY:

Random experiment: The process which when performed results different

possible outcomes or cases are known as the experiment. An experiment in which
the result can’t be predicted with certainty in advance is known as random
experiment. The set of all possible outcomes is called the sample space of the
random experiment.

Trial and event:Performing a random experiment is called a trial. A subset of a

sample space is called an event. Each of the event is also termed as favourable
cases or events.

Exhaustive cases:the number of cases which includes all possible outcomes of a

random experiment is said to be the exhaustive cases for the experiment.

Equally likely cases:Two or more events are said to be equally likely events if, the
chance of their occurrence in the random experiment is equal.

Mutually exclusive cases: Two or more events are said to be mutually exclusive if,
their simultaneous occurrence is not possible. While tossing a coin, getting event
head and event tail is an example of mutually exclusive cases.

1 Prof. Balaram Pd. Sharma

Independent cases(events):Two events are said to be independent events if, the
occurrence of one event doesn’t affect the occurrence of the other one. For
example: the occurrence of tail in tossing a coin is independent of getting 6 on
rolling the dice.

Dependent cases(events): A set of events is said to be dependent if, the

occurrence and non-occurrence of one event in any trial affects the other
subsequence trial. Example: If two cards are drawn from a well-shuffled deck of
52 cards, the result of getting second card depends upon the obtained result of
the first card. While, the occurrence of head or tail doesn’t depend upon the
result of previous toss in tossing of two coins.

CLASSICAL OR PRIORI DEFINITION OF PROBABILITY:

Let n be the number of mutually exclusive, equally likely and exhaustive outcomes
of a random experiment and n be the number of outcomes favourable to an event
A associated with the experiment. The probability of an event A, denoted by P(A)
is defined as,
𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑢𝑟𝑎𝑏𝑙𝑒 𝑐𝑎𝑠𝑒𝑠 𝑚
P(A) = =
𝑡𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑎𝑙𝑙 𝑝𝑜𝑠𝑠𝑖𝑏𝑙𝑒 𝑐𝑎𝑠𝑒𝑠 𝑛

Note: [i]. 0 ≤ P(A) ≤ 1

[ii]. If, P(A) = 0, event A is said to be an impossible event.

[iii]. If, P(A) = 1, event A is said to be a sure event.

[iv]. P(A’) = 1- P(A), where P(A’) or P(𝐴̅) denotes the probability of

nonoccurrence or non-happening of an event A.

[v]. P(A) and P(A’) are said to be complementary probabilities.

[vi]. Classical definition can’t be used in the case of not equally likely event.

[vii]. This definition fails if total number of possible cases is infinite.

2 Prof. Balaram Pd. Sharma

Empirical definition:If an event A occurs m times in n number of repetitions of a
random experiment, then the value of the relative frequency m/n, when n
becomes sufficiently large is said to be probability of happening of the event A.
𝑚
Hence, P(A) = lim [ ], provided the limit exists.
𝑛→∞ 𝑛

Permutation and combination: the concept of permutation and combination may

be useful in the study of probability theory. So we discuss only about meaning,
notations and formula of permutations and combinations.

The permutation of a given set of objects is defined as the ordered arrangement of

these objects taken some or all at a time.

Note: [i]. The total number of permutations of n objects taken r at a time is

𝑛!
denoted by P(n,r),which is formulated as, P(n,r) = (𝑛−𝑟)! Type equation here.

If, all objects are taken at a time [i.e. n=r], then, P(n,r) = n! ( because of 0! =1)

[ii]. Out of total n objects if, first kind of objects is repeated ‘q’ times,
second kind repeated ‘r’ times, third kind ‘s’ times and so on; the total number of
𝑛!
permutations in such cases is given by, P(n) =
𝑞!𝑟!𝑠!..

The combination of a given set of objects means the arrangements without any
regard to order. The absence of order in the combination of items makes it
different from permutations of the objects. Total number of combinations of a
given set of ‘n’ objects taken ‘r’ at a time, is denoted by C(n,r) and is formulated
𝑃(𝑛,𝑟) 𝑛!
as, C(n,r) = = (𝑛−𝑟)!
𝑟!

Note:[i]. Complementary combinations: the number of combinations of ‘n’ things

taken ‘r’ at a time is equal to the number of combinations of ‘n’ thing taken ‘n-r’at
a time. Symbolically, C(n,r) = C(n,n-r).

[ii]. If C(n,r) = C(n,r’), then r+r’ = n.

[iii]. C(n,r) + C(n,r-1) = C(n+1,r)

3 Prof. Balaram Pd. Sharma

[iv]. If n=r, then C(n,r) = C(n,n) = 1. So there is only one combination of n objects
taking all at a time.

Worked out examples.

Ex.[1]. A coin is tossed successfully three times. Find the probability of getting
(a).head and tail alternately. (b) at least one tail. (c)exactly two heads.

Solution: when a coin is tossed three times we may have the following
possibilities.

First toss: T T T T H H H H

Second toss:T T H H T T H H

Third toss: T H T H T H T H

The sample space is, S = {TTT,TTH,THT,THH, HTT, HTH, HHT, HHH} ∴ n(S) = 8

(a) if A be an event of getting head and tail alternately, then n(A) = 2

where A ={THT, HTH}.
𝑛(𝐴)
Required probability, P(A) = =2/8 = 1/4.
𝑛(𝑆)

(b) if, B an event of getting at least one tail, then n(B) = 7

where B ={TTT,TTH,THT,THH, HTT, HTH, HHT}
𝑛(𝐵)
Hence, required probability, P(B) = = 7/8
𝑛(𝑆)

(c) if E be an event of getting exactly three heads, then n(E) = 1, where E = {HHH}
𝑛(𝐸)
Hence, the required probability, P(E) = = 1/8
𝑛(𝑆)

Ex.[2]. A box contains 6 blue, 10 black and 5 yellow balls. if 3 balls are drawn at
random, what is the probability that three ball drawn are (a) one of each color.
(b) two blue and one other.

4 Prof. Balaram Pd. Sharma

Solution: total number of balls in the box =6 + 10 + 5 = 21. The three balls can be
selected out of 21 balls in C(21,3) different ways.
then, total number of possible cases, n = C(21,3).

(a) the favorable nos. of cases for 1 blue, 1 black and 1 yellow ball
m = C(6,1).C(10,1).(5,1)

Hence, the probability of getting 3 balls one of each color

C(6,1).C(10,1).C(5,1) 6𝑋 10𝑋 5
= m/n = = =30/133
𝐶(21,3) 1330

(b) Here, total no. of blue balls = 6, total no. of others = 10+5 = 15.

Two blue balls can be selected in C(6,2) ways. One other ball can be selected in
C(15,1) ways. Number of favorable cases of getting 2 blue & 1 other

m = C(6,2).C(15,1)

Finally probability of getting two blue balls and one other is,
𝐶(6,2).𝐶(15,1) 15 𝑋 15
P = m/n = = =225/1330 = 0.17
𝐶(21,3) 1330

Ex.[3]. There are 3 economists, 4 mathematician,2 statistician and 1 pilot. A

committee of 4 among them is to be formed. Find the probability that the
committee:

(a) consists of one of each kind.

(b) has at least one mathematician.

(c) has a pilot as a member and 3 others.

Solution: total number of persons = 10. Total number of possible cases ‘n’ is the
no. of ways in which 4 members can be selected out of 10. So, n = C(10,4)

(a) Now m = number of favorable cases for the committee consisting one of each
professional = C(3,1).C(4,1).C(2,1).C(1,1).

Required number of probability ,

5 Prof. Balaram Pd. Sharma

 C(3,1).C(4,1).C(2,1).C(1,1). 3𝑋4𝑋2𝑋1
P = m/n = = = 24/210 =4/35
𝐶(10,4) 210

(b) Probability ‘P’ that the committee consists of at least one mathematician is
P= prob.[1 mathematician, 3 others] + prob.[2 mathematician, 2 others]
+ prob.[3 mathematician, 1 other] +prob.[4 mathematician].
𝐶(4,1).𝐶(6,3) 𝐶(4,2).𝐶(6,2) 𝐶(4,3).𝐶(6,1) 𝐶(4,4).𝐶(6,0)
= + + +
𝐶(10,4) 𝐶(10,4) 𝐶(10,4) 𝐶(10,4)

= 1/210[80+ 90 + 24 + 1] = 195/210 = 13/14

(c) let P be the probability that the committee consisting of 1 pilot and 3 others.
Number of favorable cases consisting of 1 pilot and 3 others(out of 9others) ‘m’ =
𝐶(1,1). 𝐶(9,3)
𝑚 𝐶(1,1).𝐶(9,3)
Required probability of such committee = = = 84/210 = 2/5
𝑛 𝐶(10,4)

Ex.[4]. Three groups contain 3 men & 1 woman; 2 men & 2 women; 1man & 3
women respectively. One worker is selected at random from each group. What is
the prob. That the group selected consists of 1 man and 2 women.

Solution: let M, W denote the selection of man and woman from 3 groups A, B &C
respectively.

Group A:[3M, 1W] Group B:[2M, 2W] Group C:[1M, 3W]

The prob. ‘P’ that the group selected consists of 1 man and 2 women is,

P = prob.[1M from A, 1W from B, 1W from C]+prob.[1W fm A, 1M fm B, 1W fm C]

+ prob.[1W fm A, 1W fm B, 1M fm C]
𝐶(3,1) 𝐶(2,1) 𝐶(3,1) 𝐶(1,1) (2,1) 𝐶(3,1) 𝐶(1,1) 𝐶(2,1) 𝐶(1,1)
= . . + . . + . . .
𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1) 𝐶(4,1)

= 9/32 + 3/32 + 1/32 = 13/32.

Ex.[5]. A leap year is selected at random. What is the probability that it will
contain 53 number of Saturdays?

6 Prof. Balaram Pd. Sharma

Solution: A leap year consists of 366 days. So, a leap year consists of 52 complete
weeks and 2 odd (extra) days. The remaining two more (extra) days may come
with any one of the following combinations.

Sun Mon Tue Wed Thu Fri Sat

Mon Tue Wed Thu Fri Sat Sun

Tue Wed Thu Fri Sat Sun Mon

------------------------------------------------------------

Fri Sat Sun Mon Tue Wed Thu

Sat Sun Mon Tue Wed Thu Fri

53number of Saturdays exists when it consists of next 1 Saturday in extra 2 days

out of the above combinations.

Here, n = 7 and m = 2.

Therefore, prob. having 53 Saturdays = m/n = 2/7.

TWO BASIC LAWS OF PROBANILITY

Addition theorem [law of total probability]:

Statement : If A and B are two events with their respective probabilities P(A) and
P(B), then the probability of occurrence of at least one of these two events,
denoted by P(A ∪ B) is given by P(AUB) = P(A) + P(B) - P(A∩B)

Where P(A ∩B) is the probability of the simultaneous occurrence of the events A
and B.

Proof :let n be the total number of equally likely and exhaustive outcomes of a
random experiment. If u, v, w be the number of cases favorable to the event A, B
and A∩B respectively. then

P(A) = u/n, P(B) = v/n, P(A∩ B) = w/n.

7 Prof. Balaram Pd. Sharma

Since, the outcome w are common number to both events A and B. so number of
cases favorable to event A∩ B is u+v-w.

Thus, P(A UB) = [u+v-w]/n = u/n + v/n –w/n

= P(A) + P(B) – P(A∩B)

Notes:[i]. If A and B are two mutually exclusive events, then P(A∩ B) = 0,

in this case, P(AUB) = P(A) + P(B).

[ii]. If A,B,C are three events, then probability of occurrence of at least one
of these events is given by,

P(AUBUC)=P(A)+P(B)+P(C)-P(A∩B)-P(B∩C)-P(A∩C)+P(A∩B∩C).

[iii]. If A,B,C are three mutually exclusive events, then

P(AUBUC)=P(A)+P(B)+P(C).

[iv]. Probability of occurrence of at least one of the event A and B is also

denoted byP(A or B).

Multiplication theorem [law of compound probability]:

Statement: If two events A and B are independent, then the probability of their
simultaneously occurrence is equal to the product of their individual probabilities.
i.e., P(A∩B) = P(A) .P(B)

Proof: Let n’ and n’’ be total number of possible cases for the events A and B
respectively with m’ and m’’ their respective favorable cases. Then,
P(A) = probability of occurrence of event A = m’/n’.
and P(B) = probability of occurrence of event B = m’’/n’’.

Since, the total number of possible cases for the events A and B are n’ and n’’
respectively. so, the total number of possible cases for their simultaneous
occurrence is n’.n’’. similarly the total number of favorable cases for the
simultaneous occurrence for event A and B is m’.m’’.

8 Prof. Balaram Pd. Sharma

 Thus, P(A B) = probability of simultaneous occurrence of A and B
= [m’.m’’]/[n’.n’’] = [m’/n’] .[ m’’/n’’] = P(A).P(B)

∴P(A∩B) = P(A).P(B)

Notes:[i]. If A, B, C are three independent events, then the probability of their

simultaneous occurrence is given by, P(A∩B∩C) = P(A).P(B).P(C)
[ii].# Probability that event A will not happen is, P(A’) = 1 – P(A).
#probability that non of two independents A and B will happen is:
P(A’).P(B’) = [1-P(A)].[1-P(B)]
#probability that at least one of the two events will happen is,
P(AUB) = 1 - P(A’).P(B’) = 1 – [1-P(A)].[1-P(B)].
Note[iii]. The probability of simultaneous occurrence of two independent events
A and B i.e. P(A∩B) can also be denoted by, P(A and B) or P(A.B)

Worked out examples:

Ex.[1]. A problem in statistics is given to solve for 5 students A, B,C,D and E. Their
chance of solving are 1/2, 1/3, 1/4, 1/5 and 1/6 respectively. What is the
probability that the problem will be solved.

Solution: Probability that A can’t solve the problem = 1 – 1/2 = 1/2.

Probability that B can’t solve the problem = 1 – 1/3 = 2/3.
Probability that C can’t solve the problem = 1 – 1/4 = 3/4.
Probability that D can’t solve the problem = 1 – 1/5 = 4/5
probability that E can’t solve the problem = 1 – 1/6 = 5/6 probability that all the
three students can’t solve the problem
. = [1/2].[ 2/3].[3/4].4/5].[5/6] = 1/6
the problem will be solved if, any one will be able to solve it.

Therefore, the probability that the problem will be solved = 1 – 1/6 = 5/6.

Ex.[2]. A bag contains 8 white and 4 red balls. 5 balls are drawn at random. What
is the probability that 2 of them are red and 3 white.

Solution : Total number of balls in the bag = 4 + 8 = 12, Number of balls drawn = 5
number of ways in which 5 balls can be drawn out of 12 = C(12,5).number of ways
9 Prof. Balaram Pd. Sharma
in which 2 red balls can be drawnout of 4 = C(4,2).
Number of ways in which 3 white balls can be drawn from 8 = C(8,3).
the number of favorable cases for the event of getting 2 red and 3 white,

m = C(4,2).C(8,3)
total number of possible cases, n = C(12,5).

Hence, required probability, P = m/n = [C(4,2).C(8,3)]/C(12,5)

= 14/33 = 0.424

Ex.[3]. A bag contains 5 white and 8 red balls. Two drawing of three balls are
made such that (a) the balls are replaced before the second trial. (b) the balls are
not replaced before the second trial. Find the probability that the first drawing
will give 3 white and second give 3 red balls in each case.

Solution: (a). when the balls are replaced before the second trial.
Total numbers of balls in the bag =5 + 8 = 13 .now, 3 balls can be drawn out of 13
in C(13,3) ways. Also, 3 white balls can be drawn
out of 5 in C(5,3) ways. And 3 red balls can be
drawn from 8 in C(8,3) ways.

The probability of 3 white balls in the first trial = C(5,3)/C(13,3) =5/143 The
probability of 3 red balls in the second trial (after replacing the first trial) .
C(8,3)/C(13,3) = 24/143.

Hence, the probability of getting 3 white balls in the first trial and 3 red balls in
the second trial = [5/143].[28/143] = o.007
(b).when the balls are not replaced.

At first trial, 3 white balls can be drawn in C(5,3) ways.

Probability of drawing 3 white balls in the first trial = C(5,3)/C(13,3) = 5/143

When the balls are not replaced, the total number of balls in the 2nd trial = 10
then, the probability of 3 red balls in 2nd trial = C(8,3)/C(10,3) = 7/15

Hence, the probability of compound event = [5/143].[7/15] = 7/429 = 0.016

10 Prof. Balaram Pd. Sharma

Ex.[4]. The odds against A solving a problem is 8:6 and odds in favor of B solving
the same problem is 14:10. What is the probability that :
(a).both and B will solve it. (b). A solves but B fails to solve it.
(c). none of them solve it. (d). the problem will be solved, if both try
independently each other.

Solution: let E and F denote the event of solving the problem by A and B
respectively .Then, P(E) = 6/[8+6] = 3/7

P(F) = 14/[14+10] = 7/12

(a). probability of both A and B will solve the problem [= P(A∩B)] = P(A).P(B)
=[3/7] .[7/12] = 1/4

(b). probability that the problem will not be solved by A [= P(A’)] = 1-3/7 =4/7

Probability that the problem will not be solved by B [=P(B’)] = 1-7/12 =5/12

Probability that the problem will be solved by A but not by B [=P(A and B’)]
= P(A).P(B’) = [3/7] . [5/12] = 5/28

Probability that none of them will solve the problem =P(A’ and B’)
=P(A’).P(B’) = [4/7].[5/12] = 5/21

(C). the problem will be solved if, at least one of them will solve the problem.

Hence, the probability that the problem will be solved = 1-P(A’ and B’)
= 1 - 5/21 = 16/21

CONDITIONAL PROBABILITY:

If A and B are two dependent events, then the probability of

occurrence of event B given that event A has already happened is denoted by
P(B/A).

Theorem:If A and B are two dependent events, then the conditional probability of
B given that A is already happened, is P(B/A) = P(AB)/P(A).

11 Prof. Balaram Pd. Sharma

Proof: Suppose a is the number of cases for the event of simultaneous occurrence
of A and B out of a+b number of cases in which A can happen with or without
happening of event B.
𝑎/𝑛
Then P(B/A) = a/[a+b] = [𝑎+𝑏]/𝑛 = P(AB)/P(A)

Hence, P(AB) = P(A) . P(B/A)

Similarly we can show that, P(AB) = P(AB)/P(B)

Hence, P(AB) = P(B) .P(A/B)

Note: If A,B and C are three dependent events, then, P(ABC)=P(A).P(B/A).P(C/AB)

Proof, P(ABC) = P[(AB)C] = P(AB).P(C/AB) = P(A).P(B/A).P(C/AB)

WORKED OUT EXAMPLES:

EX.[1]. A bag contains 5 white and 3 black balls. 2 balls are drawn at random one
after another without replacement. Find the probability that both balls drawn are
black.

Solution: total number of balls in the bag = 5+ 3 = 8. Let A denote the event of
drawing a black ball in first draw. B denote the event of drawing black ball in
second drawing.

Now probability of drawing a black ball in first attempt, P(A) = 3/[5+3] = 3/8

Also, probability of drawing the second black ball given that the first drawn ball is
black, P(B/A) = 2/[5+2] = 2/7

Finally, the probability that both ball drawn are black is given by,

P(AB) = P(A).P(B/A) = [3/8].[2/7] = 3/28

EX.[2]. Find the probability of drawing a queen, a king and an ace in that specified
order from a pack of card in three consecutivedraws. The cards drawn are not
being replaced.

12 Prof. Balaram Pd. Sharma

Solution:[first method]: Probability of drawing a queen in first draw = 4/52. There
are 51 cards left. Then, probability of drawing a king in second draw = 4/51.
Remaining number of cards now is 50. The probability of drawing an ace in third
draw =4/50

Since these are dependent event, probability of the compound event

= [4/52].[4/51].[4/50] = 64/132600 ==0.00048.

[second method]: Let A denotes the event of getting a queen in first draw. B
denotes the event of getting a king in second draw and C denotes the event of
getting an ace in third draw.

Now, probability of drawing a queen in first draw, P(A) = 4/52.

Again prob. of drawing a king after a queen has been drawn, P(B/A) = 4/51.

And prob. of drawing an ace given that a queen and a king have been already
drawn, P(C/AB) = 4/50.

Hence, prob. of drawing a queen , a king and an ace in the required order. P(ABC)

= P(A).P(B/A).P(C/AB) =[4/52].[4/51].[4/50] = 0.00048

Ex.[3]. A box contains 8 electric bulbs of which 3 are defectives. 2 bulbs are drawn
at random one after another without replacement. Find the probability that both
the bulbs drawn are (a) defective (b) non-defective.

Solution: total number of bulbs = 8. Number of defective bulbs = 3.

Number of non-defective bulbs = 8 - 3 = 5.

(a). Let A denotes the event of drawing defective bulb in the first draw and B
denotes the event of drawing the defective bulb in the second draw.
Therefore, P(A) = 3/8.
P(B/A) is the probability of drawing defective bulb in the second draw given that
first draw is defective. ∴P(B/A) = [3-1]/[8-1] = 2/7.

Hence, the probability that both the bulb drawn are defective,
P(A.B) or P(A and B) = P(A).P(B/A) = [3/8].[2/7] = 3/28.

13 Prof. Balaram Pd. Sharma

(b). Let A denotes the event of drawing non-defective bulb in the first draw and B
denotes the event of drawing the non-defective bulb in the second draw.
Therefore, P(A) = 5/8.
P(B/A) is the probability of drawing defective bulb in the second draw given that
first draw is defective. ∴P(B/A) = [5-1]/[8-1] = 4/7.

Hence, the probability that both the bulb drawn are non-defective,
P(A.B) or P(A and B) = P(A).P(B/A) = [5/8].[4/7] = 5/14

Ex.[4]. A record of a forest based factory shows the following analysis of its 200
workers

Qualification Age years

Below 25 25 – 35 Above 35 Total
M.A. 10 30 10 50
B.A. only 90 20 40 150
Total 100 50 50 200
If one worker is selected at random for the training from the company. Find

(i) the probability that he/she has the qualification of M.A.

(ii). The prob. that he/she is B.A .only given that he/she is below 25 yrs.
(iii). The prob. that he/she is above 35 yrs. Provided that he/she has M.A
degree.Solution: let A denote the event of selecting a worker having M.A
qualification. The event of selecting a worker having qualification B.A only is
denoted by B. The event of selecting a worker having below 25 yrs is denoted by
C.

D be the event of workers selecting above 35 yrs.

(i). the probability that he/she has the qualification of M.A. P(A) = 50/200 = 1/4.

(ii). The prob. that he/she is B.A .only given that he/she is below 25 yrs.P(B/C) =
90/200
P(B and C)/P(C) = = 9/10.
100/200

(iii). The prob. that he/she is above 35 yrs provided that he/she has M.A degree.
10/200
P(D/A) = P(D.A)/P(A) = = 1/5.
50/200

14 Prof. Balaram Pd. Sharma

EX.[5]. In a certain town males and females are equal in number. It is known that
20% of the males and 5% of the females are unemployed. A research student
studying the employment situation, selects unemployed person at random. What
is the probability that the person selected is: (a) male. (b) a female.

Solution: suppose no. of male = no. of female= 100 (say)

Employed Unemployed Total

Male 80 20 100
Female 95 5 100
Total 175 25 200
If one unemployed people is selected at random,
𝑛𝑜.𝑜𝑓 𝑢𝑛𝑒𝑚𝑝𝑙𝑜𝑦𝑒𝑑 𝑚𝑎𝑙𝑒
(a). P(male) = m/n = = 20/25 = 0.8
𝑛𝑜.𝑜𝑓 𝑢𝑛𝑒𝑚𝑝𝑙𝑜𝑦𝑒𝑑 𝑝𝑒𝑜𝑝𝑙𝑒

𝑛𝑜.𝑜𝑓 𝑢𝑛𝑒𝑚𝑝𝑙𝑜𝑦𝑒𝑑 𝑓𝑒𝑚𝑎𝑙𝑒

(b). P(female) = m/n = =5/25 = 0.2
𝑛𝑜.𝑜𝑓 𝑢𝑛𝑒𝑚𝑝𝑙𝑜𝑦𝑒𝑑 𝑝𝑒𝑜𝑝𝑙𝑒

EX.[6].In an examination 30% student failed in Forest management, 20% student

failed in wild life management and 10% failed in both subjects. A student is
selected at random, what is the probability that the student has failed in Forest
management, if it is known that he has already failed in Wild life management.

Solution: Let F be an event of student sailed in Forest management and W be that

of in Wild life management.

According to question, P(F)=30/100=3/10, P(W)=20/100= 1/5, P(F.W)=1/10

Hence, the prob. that the student has failed in Forest management if, he has
1/10
failed in Wild life management, P(F/W) = P(F.W)/P(W) = = 1/2.
1/5

EX.[7]. The probability that a person stopping at petrol pump will get tire checking
0.12 and the probability of getting fuel checking is o.29 and probability of getting
both checking is 0.07. Find the probability that
(a) he will have neither tire checking nor fuel checking. (b). he will have fuel
checking when already tire is checked.

15 Prof. Balaram Pd. Sharma

Solution: Let P(T) = probability that he will get tire checking = 0.12, P(F) =
probability that he will get fuel checking = 0.29, P(F∩T) = 0.07
̅̅̅̅̅̅) = probability that he will get neither tire checking nor fuel checking.
(a). P(𝐹𝑈𝑇

= 1 – P(FUT) = 1- [P(F) + P(T) – P(F∩T)]

=1 – [0.29+0.12-0.07] = 1- 0.34 = 0.66

(b). P(F/T) = probability that he will get fuel checking when tire is already
checked= P(F∩T)/P(T) = 0.07/0.12 = 0.58

EX.[8]. Two candidates A and B are applying for the post of manager of a
company. The probability that A and B will select are 0.8 and 0.7 respectively. if A
is selected, the probability of introducing the bonus system is 0.4 and 0.6 is the
corresponding probability if, B is selected. What is the probability that the bonus
system is introduced.

Solution: Let, P(E) = probability of selection of A = 0.8

P(F) = probability of selection of B = 0.7

Let Z be an event that bonus system is introduced, Now, P(Z) = ?

where P(Z/E) = 0.4 and P(Z/F) =0.6,

Now, P(Z) = P(Z∩E) + P(Z∩F) = P(E).P(Z/E) + P(F).P(Z/F)

=[0.8].[0.4] + [0.7].[0.6] = 0.32+0.42 =0.74

EX.[9]. A bag contains 15 pens out of which 2 are defective. One pen is taken at
random from a bag without replacement. What is the probability that (a) both are
defective (b) both are non-defective. [Hint: similar to EX.3].

BAYE’S THEOREM

If an event ‘A’ can only happen in conjunction with one of the n mutually
exclusive and exhaustive events E1,E2,E3,…………… ,En and if event A actually

16 Prof. Balaram Pd. Sharma

happens i.e.[P(A) ≠ 0], then the probability that it was proceed by the particular
event Ei(i=1,2,3,……..,n)is given by,
𝐴
𝑃(𝐸𝑖 ).𝑃( )
𝐸𝑖
P(Ei/A) = 𝐴
𝛴𝑃(𝐸𝑖 ).𝑃( )
𝐸𝑖

This formula is the main formula of Baye’s theorem. In particular, [if i = 1],
𝐴
𝑃(𝐸1 ).𝑃( )
𝐸1
P(E1/A) = 𝐴 𝐴 𝐴
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+⋯……….+𝑃(𝐸𝑛 ).𝑃( )
𝐸1 𝐸2 𝐸𝑛

Note:[i]. The probabilities P(E1), P(E2), ……………..,P(En) which are already given or
known before conducting an experiment. These probabilities are called ‘prior’ or
‘priori’.
[ii]. The conditional probabilities P(E1/A), P(E2/A), …………….P(En/A), which are
computed after conducting the experiment are called ‘posteriori’ or ‘revised’
probabilities.
[iii]. Particularly, if E1 and E2 are two mutually exclusive events such that P(E1)
+ P(E2) = 1, then for E2, Baye’s theorem can be written as,
𝐴
𝑃(𝐸2 ).𝑃( )
𝐸2
P(E2/A) = 𝐴 𝐴
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )
𝐸1 𝐸2

[iv]. The computation can be presented in the following table:

Events[E] Prob. of event E Conditional prob. of Ai, P(Ei).P(Ai/Ei)

i.e. P(E) given Ei
E1 P1 P(A1/E1) P(E1).P(A1/E1)
E2 P2 P(A2/E2) P(E2).P(A2/E2)
Total 1.00 2
𝐴𝑖
∑ 𝑃(𝐸𝑖). 𝑃( )
𝐸𝑖
𝑖=1

Worked out examples:

17 Prof. Balaram Pd. Sharma

Ex.[1]. A company has two plants to manufacture scooters. Plant A produces 80%
of the scooters and plant B produces 20%. At plant A, 85 out of 100 scooters are
rated as standard (better) quality at plant B only 65 out of 100 scooters are rated
standard. What is the probability that the scooters selected at random came from
plant B, if it is known that scooter is of standard quality.

Solution: Let E1 and E2 be the events of scooters manufactured by plant A and B

respectively. A be an event of better or standard quality scooters.

Given that, P(E1) =80/100 =0.8, P(E2)=20/100 = 0.2, where, P(E1)+P(E2) =1,
Also, P(A/E1) = 0.85, P(A/E2) = 0.65

Probability of scooters manufactured by plant B, which are of standard quality

P(E2/A) =?

By Baye’s theorem,
𝐴
𝑃(𝐸2 ).𝑃( ) 0.2 𝑋 0.65
𝐸2
P(E2/A) = 𝐴 𝐴 =
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( ) 0.8 𝑋 0.85+0.2 𝑋 0.65
𝐸1 𝐸2

= 0.13/[0.13+0.68] = 0.13/o.81 = 0.16

Ex.[2]. There are three machines producing 10000; 20000 and 30000 bullets per
hour respectively. These machines are known to be producing 1%, 2% and 1%
defective respectively. One bullet is taken at random from one hours production
of the three machines and found to be defective. What is the probability that this
bullet is from (a) 1st machine. (b) 2nd machine. (c) 3rd machine.

Solution: Let E1, E2 and E3denote the events of production of bullets per hour by
first, second and third machine respectively. A be the event of defective bullets.
10000
The priori probabilities are , P(E1) = = 10000/60000 = 1/6,
10000+20000+30000

P(E2) = 20000/60000 = 1/3, and P(E3) =30000/60000 = 1/2 .

Where, P(E1) + P(E2) + P(E3) = 1, [which is true]

Also, P(A/E1) =1/100, P(A/E2) = 2/100, and P(A/E3) =1/100.

18 Prof. Balaram Pd. Sharma

(a). Now, probability of bullets produced from first machine which is defective,
𝐴 1 1
𝑃(𝐸1 ).𝑃() .[ ]
𝐸1 6 100
P(E1/A) = 𝐴 𝐴 𝐴 = 1 1 1 2 1 1
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+𝑃(𝐸3 ).𝑃( ) [ ].[ ]+[ ].[ ]+[ ].[ ]
6 100 3 100 2 100
𝐸1 𝐸2 𝐸3

1/600 1/600
= 1 2 1 = = 1/8
+ + 8/600
600 300 200
(b). Again probability of bullets produced from second machine which is defective,
𝐴 1 2
𝑃(𝐸2 ).𝑃() .[ ]
𝐸2 3 100
P(E2/A) = 𝐴 𝐴 𝐴 = 1 1 1 2 1 1
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+𝑃(𝐸3 ).𝑃( ) [ ].[ ]+[ ].[ ]+[ ].[ ]
6 100 3 100 2 100
𝐸1 𝐸2 𝐸3

2/300 2/300
= 1 2 1 = = 1/2
+ + 8/600
600 300 200

(b). Again probability of bullets produced from third machine which is defective,
𝐴 1 1
𝑃(𝐸3 ).𝑃() .[ ]
𝐸3 2 100
P(E3/A) = 𝐴 𝐴 𝐴 = 1 1 1 2 1 1
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+𝑃(𝐸3 ).𝑃( ) [ ].[ ]+[ ].[ ]+[ ].[ ]
6 100 3 100 2 100
𝐸1 𝐸2 𝐸3

1/200 2/300
= 1 2 1 = = 3/8
+ + 8/600
600 300 200

EX.[3]. A factory has three units A, B and C. A produces 25%b0f its products. Unit
B produces 25% and C produces 50%. If the percentage of defective item
produced by 3 units A, B and C are respectively 1%, 2% and 3% . An item selected
randomly from the total production of the factory is found to be defective. What
is the probability that it is produced from the unit C?

Solution: Let E1, E2 and E3 be the events of products respectively produced by

three units A, B and C. Suppose the event of defective products be A. then, the
priori probabilities are;
P(E1) = 25/100 =1/4, P(E2) =25/100 = 1/4 and P(E3) = 50/100 = 1/2.
Also, P(A/E1) =1/100, P(A/E2) = 2/100, P(A/E3) = 3/100.

19 Prof. Balaram Pd. Sharma

By Baye’s theorem,
The probability that a product produced by unit C which is defective,
𝐴 1 3
𝑃(𝐸3 ).𝑃( ) .[ ]
𝐸3 2 100
P(E3/A) = 𝐴 𝐴 𝐴 = 1 1 1 2 1 3
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+𝑃(𝐸3 ).𝑃( ) [ ].[ ]+[ ].[ ]+[ ].[ ]
4 100 4 100 2 100
𝐸1 𝐸2 𝐸3

3/200 3/200
= 1 2 3 = = 2/3 .
+ + 9/400
400 400 200
EX.[4]. In a certain University the percentage of Brahmin, Chhetri and Newar out
of the students are 50, 25 and 25 respectively. If 50% of Brahmin, 90% of Chhetri
and 80% of Newar are vegetarian,Find the probability that a randomly selected
vegetarian student is chhetri.

Solution: Let E1, E2, and E3 are events of students which are Brahmin, Chhetri and
Newar respectively. An event of vegetarian student is denoted by A. now, the
priori probabilities are ;

P(E1) = 50/100 = 1/2 , P(E2) = 1/4, and P(E3) = 1/4 . Also, the
probability of vegetarian who is Brahmin, P(A/E1) = 50/100 = 1/2 . similarly,
P(A/E2) = 90/100 = 9/10, and P(A/E3) = 80/100 = 8/10. Hence,the
probability that a randomly selected vegetarian is Chhetri,P(E2/A] =?By Baye’s
theorem,
𝐴 1 9
𝑃(𝐸2 ).𝑃( ) [ ].[ ]
𝐸2 4 10
P(E2/A) = 𝐴 𝐴 𝐴 = 1 1 1 9 1 8
𝑃(𝐸1 ).𝑃( )+𝑃(𝐸2 ).𝑃( )+𝑃(𝐸3 ).𝑃( ) [ ].[ ]+[ ].[ ]+[ ].[ ]
2 2 4 10 4 10
𝐸1 𝐸2 𝐸3

9/4𝑜
=1 9 8 = 9/27 = 1/3
+ +
4 40 40

20 Prof. Balaram Pd. Sharma

 RANDOM VARIABLE :

A variable whose value is determined by the outcome of a random

experiment is called a random variable. A random variable is also known as
a chance variable or stochastic variable.

A random variable may be discrete or continuous. If the random variable

takes on the integer values such as 0, 1, 2, 3, ………, then it is called discrete
random variable. The number of print mistakes in each pages, the number
of telephone calls received by a telephone operator, total number of goals
in a football competition etc. are the examples of discrete random variable.

If the random variable takes on all values within a certain interval, such
random variable is known as continuous random variable. Amount of rain
fall on a rainy day (or season), the height and weight of individual, the
length and breadth of each of the log on a chatta are the examples of the
continuous random variables.

Detail examples of discrete random variables:

[i] A coin is tossed twice, then all the possible outcomes of that experiment
is given by, S = {HT,TH,TT,HH}, where S denotes the sample space. Let X be
a variable that it value is associated with the number of heads of the
outcomes in the experiment. Then,

Outcomes of experiment: HH HT TH TT
Random variables (X) : X1=2 X2=1 X3=1 X4=0
[ii]. If a coin is tossed three times, X be a variable that its value is associated with
the number of tails of the outcomes in an experiment.Then,

Outcomes of experiments: HHH HHT HTH THH HTT THT TTH TTT
Random variables (X): 0 1 1 1 2 2 2 3

Probability distribution of discrete random variables:

Let the discrete random variable takes the values x1, x2, x3,……………, xnwith

21 Prof. Balaram Pd. Sharma

respective probabilities p1, p2, p3, ………, pn such that p1+ p2+ p3+ ………+ pn = 1 and
0 ≤ pi≤ 1. Then the probability distribution of discrete random variable X is the
specification of the set of values Xi (i=1, 2, 3, …., n) together with their respective
probabilities pi (i=1, 2, 3, …, n). In other words,
pi = P (xi) = P (X=Xi) such that: [i] 0 ≤ P(X) ≤ 1, and
[ii] ∑ P(x) = P(x1+x2+x3+………+xn) = 1. The summation being taken over all the
values of the variable.

The function P(X) is called probability function or probability mass

function (P.M.F.) of the random variable X. The set of all possible order pair
(X, P(X) ) is called probability distribution of the random variable X. which is
expressed in table as:

Random variable (X): X1 X2 X3 X4 ……………………. xn Total

Probability P(X) : P1 P2 P3 P4 …………………… pn 1

Examples :[i]. If a fair coin is tossed successively twice, the probability distribution
of pair of variables X(getting number of heads) and respective probability are as
follows:

Outcomes : HH HT, TH TT Total

Random variables (X) : 2 1 0
P(X) : ¼ ½ ¼ 1
[ii]. If a fair coin is tossed successfully thrice, the probability distribution of pair of
random variable (number of heads) and respective probabilities are as follows;

Outcomes : HHH HHT, HTH, THH HTT, THT, TTH TTT Total
Variables (X) : 3 2 1 0
P(x) : 1/8 3/8 3/8 1/8 1
[iii]. If two dice are rolled simultaneously. X denotes the sum of the faces
numbered 1, 2, 3, 4, 5 and 6 in each. Like: probability of getting sum 4 is 3/36.
[Since, sum 4 =1+3, 2+2, 3+1], sum 4 is obtained by 3 ways. Then, the probability
distribution of a pair of sum and respective probabilities are

X : 2 3 4 5 6 7 8 9 10 11 12

22 Prof. Balaram Pd. Sharma

P(X): 1/36 2/36 3/36 4/36 5/36 6/36 5/36 4/36 3/36 2/36 1/36
Where, ∑P(X) = 1/36 + 2/36 +3/36 +4/36 +5/36 +6/36 +5/36 +4/36 +3/36 +

2/36 +1/36 = 1.

MATHEMATICAL EXPECTATION OF A RANDOM VARIABLE

The concept of mathematical expectation is of great importance in statistical

work. The expected value (or mathematical expectation) of random variable is the
weighted arithmetic mean of the variables, where the respective probabilities of
the value acts as weight of the variable. Let X denotes the discrete random
variables having values x1, x2, x3, …….., xn with respective probabilities p1, p2, p3,
….., pn, where, p1+ p2+ p3+ …..+pn = 1. Hence, the mathematical expectation or
expected value of X denoted by E(X) is defined as:

E(X) =x1p1+x2p2+x3p3+………..+xnpn

= ∑𝑛𝑖=1 𝑥𝑖 𝑝𝑖 =∑x.p(x ) ∴ E(X) = ∑x.p(x) …………………………….[i]

The mathematical expectation(or expected value) of a random variable X is also

called ‘mean of the probability distribution’

∴ 𝑀𝑒𝑎𝑛 = E(X) = ∑x.p(x) …………………………….[ii] where, E(X) =

expected value of random variable X.

Here, x = value of random variable X. and p(x) = probability that the random
variable taking the value x.

If the experiment is repeated N number of times for a single event, the expected
number of times in which an event occur is, E(X) =N.p, where p is the probability
of that event. The variance of the random variable X in term of mathematical
expectation is given by,

Var(X) = 𝜎𝑥2 = E(X2) – [E(X)]2

= ∑x2. p(x) –[∑x.p(x)]2 ……………………………………….[iii]
23 Prof. Balaram Pd. Sharma
Also, Var(X) = 𝜎𝑥2 = E[X- E(X)]2 =∑[X – E(X)]2.p(x)………….[iv]

Worked out examples:

Ex.[1]. A business man can make a profit of Rs. 30000 with a probability 0.7 or
have a loss of Rs. 20000 with a probability 0.3. What is his expected profit?

Solution: Here, loss is considered as negative profit. Hence,

Profit (X) (Rs.) : 30000 -20000

Pobability P(X): 0.7 0.3

Now, x1 = Rs. 30000, x2 = Rs. -20000, p1 = 0.7, p2 = 0.3
Expected required profit, E(X) = ∑x. p(x) = x1p1 + x2p2

= 30000 x 0.7 – 20000 x 0.3 = 15000 Hence, required expected profit

E(X) = Rs. 15,000

Ex.[2]. If it rains, an umbrella salesman can earn Rs. 400 per day. If it is fair day, he
can loss Rs.50 per day. What is his expected earning if the probability of fair day is
0.6?

Solution: Here loss is considered as negative profit. Since, probability of fair day =
0.6 means probability of rainy day = 0.4, So,

Earning (X) ‘Rs.’ : 400 -50

Probability P(X) : 0.4 0.6

Here, x1 =Rs. 400, x2 =Rs. -50, p1 = 0.4, p2 = 0.6. Wehave expected earning is,
E(X) = ∑x. p(x) = x1p1 + x2p2 = 400x0.4 -50x0.6 = 160-30 = 130

Hence, the expected profit =Rs. 130

Ex.[3]. A dealer of computers estimates from the past experience that the
probability of his selling computers in a day are as follows:

No. of computer sale per day (X): 0 1 2 3 4 5 6

Probability P(X) : 0.03 0.20 0.23 0.25 0.12 0.10 0.07

24 Prof. Balaram Pd. Sharma

Calculate the average number of computers sale per day (or expected number of
sale per day). Also compute the variance and standard deviation of the sale.

Solution: computation of mean, variance and s.d. of sale.

X P(x) x.P(x) X2 X2.P(x)

0 0.03 0 0 0
1 0.20 0.20 1 0.20
2 0.23 0.46 4 0.92
3 0.25 0.75 9 2.25
4 0.12 0.48 16 1.92
5 0.10 0.50 25 2.50
6 0.07 0.42 36 2.52
∑x.P(X)=2.81 ∑x2.P(X)=10.31

Now, average sale or expected sale(𝑋) ̅̅̅= E(X) = ∑x.P(X)=2.81 ≈ 3.

Variance of sale, 𝜎𝑥2 = ∑x2.P(X) –[∑x.P(X)]2 = 10.31 – [2.81]2 = 2.414

Finally, standard deviation of the sale=1.554.

Ex.[4]. From the following information of demand of new product, calculate the
mathematical expectation of demand. Also calculate variance and standard
deviation of demand.

Demand (in unit) X: 300 250 200 150 100 50

Probabilities P(X): 0.05 0.10 0.15 0.30 0.30 0.10
n
Sol : Computation of mean, variance and standard deviation of demand.

X P(X) x. P(X) X2 X2 .P(X)

300 0.05 15 90000 4500
250 0.10 25 62500 6250
200 0.15 30 40000 6000
150 0.30 45 22500 6750
100 0.30 30 10000 3000
50 0.10 5 2500 250

25 Prof. Balaram Pd. Sharma

 ∑x. P(X)= 150 ∑X2 .P(X)= 26750
Mathematical expectation of demand ̅̅̅̅̅
(𝑋)= E(X) = ∑x. P(X)= 150 units

Variance of demand ,𝜎x2 = ∑X2 .P(X) – [∑x. P(X)]2 = 26750-(150)2 = 4250 units

S.D. of Demand = 𝜎x= √𝜎𝑥 2 = √4250 = 65.2 ≈ 65

Ex.[5]. The probability that there is at least one error in an accounts statement
prepared by A, B and C respectively are 0.5, 0.7 & 0.8. A, B and C prepared 10, 16
and 20 number of statements respectively. Find the expected number of correct
statements in all.

Solution: Here, X = {x1, x2, x3}. Are random variables having probabilities p1, p2, p3,
respectively. where, pi are the probability of correct statements i.e.,
pi = 1-P[incorrect statement]. Hence, x1=10, x2=16, x3=20 p1=1-0.5=0.5,
p2=1-0.7=0.3, and p3=1-0.8=0.2. [sine, p1+p2+p3=1, true]

Finally, the expected value of correct statements, E(X) = 𝑋̅ = 𝛴x.P(x)

= x1p1+x2p2+x3p3 = 10x0.5+16x0.3+20x0.2= 13.8 ≈ 14 (approximately).

Ex.[6]. The random variable X has following probabilities distribution:

X: -3 -1 0 4
P(X): 0.20 0.40 0.30 0.10
Calculate the mathematical expectation of X

Soln : Here x1= -3, x2= -1, x3=0 , x4=4 and respective probabilities are,

P1=0.20, P2=0.40, P3=0.30, P4=0.10

Now, mathematical expectation of X = 𝑋̅= x1P1+ x2P2+ x3P3 + x4P4

= -3×0.20 - 1×0.40 + 0×0.30 + 4×0.10

= -0.60-0.40+0+0.40 = -0.60

Ex.[7]. The monthly demand for T.V. sets is known to have the following
distribution table
26 Prof. Balaram Pd. Sharma
Demand (X): 1 2 3 4 5 6
Probability P(X): 0.10 0.15 0.20 0.25 0.18 0.12
Determine the mathematical expectation of demand

Soln: Here, x1=1, x2=2, x3=3, x4=4, x5=5, x6=6

P1=0.10, P2=0.15, P3=0.20, P4=0.25, P5=0.18, P6=0.12

Now, Mathematical expectation of demand,

E(X) = 𝑋̅ = ∑x. P(x)

= x1P1+ x2P2+ x3P3 + x4P4+ x5P5 + x6P6

= 1(0.10) + 2(0.15) + 3(0.20) + 4(0.25) + 5(0.18) + 6(0.12)

= 0.10+ 0.30+ 0.60+ 1.0+ 0.90+ 0.72

= 3.62

EX.[8]. Find the expected sales of Toyota car in Kathmandu City in a week from
the following information:

Day: Sun Mon Tue Wed Thu Fri

Sales(X): 90 60 90 50 75 55
ProbabilityaP(X): 0.25 0.18 0.12 0.05 0.20 0.20
Solve, it !

Theoritical Distribution
❖ A function of P(X)= f(X) is called probability function of the random variable
X.
where, X= {x1, x2, ………., xn} and P(X)= {p1, p2, ………., pn}
27 Prof. Balaram Pd. Sharma
 ❖ A random variable can be of two types,
i. Discrete random variable
ii. Continuous random variable
❖ A random variable is known as discrete if the set of values defined by it
over the sample space is finite.
❖ A random variable is said to be Continuous if it can assume any real value in
an interval or a range.
❖ If the random variable X is discrete, the probability of function P(X) is called
“Probability Mass Function” (P.M.F.) or “Discrete Probability Distribution”.
❖ If the random variable X is continuous, the probability function P(X) is called
“Probability Density Function” or “Continuous Probability Distribution”

In this theoretical distribution, the following are popular:

1) Binomial distribution
2) Multinomial distribution Discrete probability distribution

3) Poisson distribution
4) Normal distribution } Continuous probability distribution

Binomial Distribution
The binomial distribution is also known as “Bernoulli’s Distribution”

Binomial distribution is a probability distribution expressing the probability

of one set as ‘success’ or ‘failure’ events.

Assumptions for binomial distribution

❖ An experiment is performed under the same conditions for a fixed no. of

trials, say ‘n’.
❖ In each trial, there are only two possible outcomes of the experiment,
which are ‘success’ or ‘failure’

28 Prof. Balaram Pd. Sharma

 ❖ The probability of a success in a trial is denoted by ‘p’ which remains
constant throughout the trial. The probability of failure is 1-p (=q).
❖ The trials are statistically independent i.e. the outcomes of any trial do not
affect the outcomes of the subsequent trials.

Probability function of binomial distribution

Suppose a random experiment of n independent trials has r success and n-r

failure for finite & fixed n. If p denotes a probability of a success & q= 1-p a
probability of a failure in one trial. Then the probability of getting exactly r success
in n independent trials is given by,

P (X=r) = P (r) = C (n,r) prqn-r ……………………………………………… (1)

Where, r= 0, 1, 2, ……….., n.
n!
Where, C (n, r) = and p+q=1.
(n−r)!r!

where parameters n and p are called binomial parameters. The value of P (r) can
be obtained if the value of n and p are known.

If r=0, 1, 2, 3, ……….,n the particular values of probability distributions are,

P(0) = C(n,0) p0qn-0=qn, P(1)= C(n,1) p1qn-1, P(2)= C(n,2) p2qn-2 ,……………………………….
P(n)= C(n,n) pnqn-n=pn

Hence, ∑𝑛𝑟=0 𝑃(𝑟) = P(0)+ P(1)+ P(2)+ ………+P(n)

= qn+ C(n,1) p1qn-1+C(n,2) p2qn-2+….+C(n,r) prqn-r+…..+pn

= (q+p)n.

Properties or characters of Binomial distribution:

• The Binomial parameters in the Binomial distribution are ‘n’ and ‘p’. If n
and p are known, the binomial distribution is completely determined.
• The binomial distribution is a discrete probability distribution because,
random variable (X) takes only integral values.(i.e. r=integer).

29 Prof. Balaram Pd. Sharma

 • Mean of the binomial distribution, 𝑋̅=np.
Variance of the binomial distribution, 𝜎 2 =npq.
Standard deviation of the binomial distribution, σ =√𝑛𝑝𝑞.
• In a binomial distribution, variance is always less than mean, [i.e., npq<np,
since q<1]
• If p=q=1/2, the binomial distribution is symmetrical.
If p>1/2, the binomial distribution is negatively skewed.
If p<1/2, the binomial distribution is positively skewed.
• If ‘np’ is an integer, the distribution is ‘unimodal’. The mean and mode of
the distribution are equal each being ‘np’.

NOTE: We denote the binomial variable X as: X~B(n,p). where ‘n’ and ‘p’ are
binomial parameters.

Fitting of Binomial distribution:

If a random experiment, having ‘n’ trials is repeated ‘N’ times satisfying the
conditions of binomial distribution, then the expected or theoretical frequency
of ‘r’ success is given by, f(r) = N.P(r) = N.C(n,r).pr.qn-r… … … … … …[1].
Particularly, if we put, r = 0, 1, 2, … … …,n we get,
f(0) = N.P(0) =N.C(n,0)p0qn-0 = N.qn , f(1) = N.P(1) = N.C(n,1)p1qn-1
f(2) = N.P(2) = N.C(n,2)p2qn-2, f(3) = N.P(3) = N.C(n,3)p3qn-3
… … … … … … … … … … … f(n) = N.P(n) = N.C(n,n)p nqn-n = N.pn
∴ ∑𝑛𝑖=1 𝑓(𝑥𝑖) = N. [qn+C(n,1)p1qn-1+C(n,2)p2qn-2+… … …+pn]

=N.(q+p)n.
If p is unknown, mean is calculated by, 𝑋̅ = 𝛴fx/N, also, np =𝑋̅ ∴ p = 𝑋̅/n
&q=1- 𝑋̅/n. By using these values of p & q the expected or theoretical
binomial frequencies can be obtained.

Worked out examples:

Ex.[1]. A fair coin is tossed 8 times considering head as success. Find the
probability of getting (i) 6 or more heads. (ii) exactly 4 heads. (iii) no heads.
(iv) not more than 2 heads.

30 Prof. Balaram Pd. Sharma

Solution: Here, number of trials, n =8,
probability of a success in a trial ( getting a head) p =1/2, then, q =1-1/2 =1/2.
(i). probability of getting 6 or more heads, P(r ≥ 6) ?
Now, P(r ≥ 6) = P(6)+P(7)+P(8)
= C(8,6)(1/2)6.(1/2)8-6+C(8,7)(1/2)7.(1/2)8-7+C(8,8)(1/2)8.(1/2)8-8
= (1/2)8 [C(8,6)+C(8,7)+C(8,8)] = 1/256[28+8+1] = 37/256.
(ii) Probability of getting exactly 4 heads, P(r=4) or P(4)=?
8𝑋7𝑋6𝑋5
Now, P(r=4)or P(4) =C(8,4)(1/2)4.(1/2)8-4 = .(1/2)8 =70/256 = 35/128
4𝑋3𝑋2𝑋1
(iii) Probability of getting no heads, P(r=0) or P(0) =?
Now, P(0) = C(8,0).(1/2)0.(1/2)8-0 = 1.(1/2)8 = 1/256
(iv).Probability of getting not more than 2 heads, P(r≤2) = ?
Now, P(r≤2) = P(0)+P(1)+P(2)
= C(8,0).(1/2)0.(1/2)8-0+C(8,1)(1/2)1.(1/2)8-1+C(8,2)(1/2)2.(1/2)8-2
= (1/2)8[C(8,0)+C(8,1)+C(8,2)] = 1/256[1+8+28] = 37/256

Finally, mean np = 8x1/2 = 4.

1 1
Also, Standard deviation S.D. = √𝑛𝑝𝑞 = √8𝑋 ( ) 𝑋( ) = √2
2 2

EX.[2]. (a).The mean and standard deviation of a binomial distribution are 15 and
5 respectively. Comment on the results.
(b). Is there any inconsistency in the statement that the mean of the binomial
distribution is 6 and variance 4? If no inconsistency is found, what are the values
of n, p and q with usual notation.

Solution: (a). For the binomial distribution, mean(np) = 15,

𝑛𝑝𝑞
variance(npq) = (S.D.)2 = 25, Now, = 25/15 = 5/3 ∴ q = 5/3 (>1) since, q > 1,
𝑛𝑝
the result is inconsistent or not consistent.

(b). For the binomial distribution, mean(np) = 6,

𝑛𝑝𝑞
variance(npq) = (S.D.)2 = 4, Now, = 4/6 = 2/3 ∴ q = 2/3 (<1) since, q < 1, the
𝑛𝑝
result is not inconsistent or consistent. So, p = 1-q = 1- 2/3 =1/3
Also, np = 6, so, n= 6/p = 6.3 = 18.
Hence, p = 1/3, q = 2/3. & n = 18.
31 Prof. Balaram Pd. Sharma
EX.[3]. If a probability of a non-defective item is 0.9 .
find (a).mean (b). variance for the distribution of defective item in a total of 400.

Solution: let p be the probability of success or probability of getting defective

item. Similarly, the probability of getting non-defective item or failure is q.
Here, q = 0.9, So, p=1– q=0.1

(a). Mean of the defective item (np) = 400 x 0.1 = 40

(b) Variance of the distribution of defective item (npq) = 400 X 1/10 X9/10 = 36

EX.[4]. Ten unbiased coins are tossed simultaneously. Find the probability of
getting (a) exactly 6 heads. (b) at least 8 heads. (c) no head. (d) at least 1 head. (e)
not more than 3 heads.

Solution: Here, probability of getting a head in a trial (p) = 1/2,

then, q = 1-p = 1-1/2 = 1/2,
n = number of tossing of a coin = 10.
(a). Probability of getting exactly 6 heads, P(r=6) or P(6) =?
10𝑋9𝑋8𝑋7
Now, P(6) = C(10,6).p6.q10-6 = .[1/2]6.[1/2]4 = 105/572.
4𝑋3𝑋2𝑋1
(b)Probability of getting at least 8 heads, P(r≥ 8) = ?
Now, P(r≥ 8) = P(8)+P(9)+P(10) =7/128
(c). Probability of getting no head, P(r=0) or P(0) = ?
We have, P(0) = C(10,0).[1/2]0.[1/2]10 = 1/1024.
(d). Probability of getting at least 1 head, P(r≥ 1) = ?
Now, P(r≥ 1) = 1-P(0) = 1- 1/1024 = 1023/1024.
(e). Probability of not more than 3 heads, P(r≤ 3) =?
We have, P(r≤ 3) = P(0)+P(1)+P(2)+P(3) = 11/64.

EX.[5]. Probability that a student will not graduate is o.6. Find the probability that
out of 5 students (a) none (b)only one (c) at least one will be graduate. [solve
yourself]

EX.[6]. The average percentage of failure in a certain examination is 40. What is

the probability that out of a group of 6 students at least 4 passed the Exam.

32 Prof. Balaram Pd. Sharma

Solution: Let p denotes the probability of a success and q that of a failure.
Here, probability of one failure (q) = 40/100 =2/5 and probability of one success
(p) = 1-q = 3/5. Also given that, n = 6 .
Now, probability that at least 4 passed the exam P(r≥ 4) = ?
We have, P(r≥ 4) = P(4)+P(5)+P(6) = C(6,4).p4q2 + C(6,5)p5q1 + C(6,6)p6q0
34 22 35 21 36 20 1
= 15. + 6. + 1. = . [4860 + 2916 + 729]
56 56 56 56

=0.544

EX.[7]. The incidence of an occupational disease in an industries is such that a

workman has a 20% chance of suffering from it. If 6 workmen are selected at
random. Find the probability that (a). exactly 3 workers contact the disease. (b).
four or more workers will contact the disease.

Solution: Here, probability that a worker has a chance of suffering from disease
(p) = 20/100 =1/5, n=6, q=1-1/5=4/5.
(b) Probability that 4 or more will contact the disease, P(r≥ 4) =?
We have, P(r≥ 4) = P(4)+P(5)+P(6)
= C(6,4)[1/5]4[4/5]2+C(6,5)[1/5]5[4/5]1+C(6,6)[1/5]6[4/5]0
1 265
= [15.1.6 + 6.1.4 + 1.1.1 ] = =0.0169
56 5 𝑋3125
(a) solve yourself.

EX.[8]. The probability of bomb hitting a pillar is 2/9. Three bombs are enough to
destroy a pillar. If 7 bombs are aimed hitting at that pillar. Find the probability
that the pillar is destroyed.

Solution: Probability of one success or probability of bomb hitting a pillar(p) = 2/9.

Now, q=1-p =7/9, n =7, P(r≥ 3 ) =?
We have, P(r≥ 3 ) = 1- P(r<3) = 1- [P(0)+P(1)+P(2)]
= 1 –[C(7,0){2/9}0{7/9}7+C(7,1){2/9}1{7/9}6+C(7,2){2/9}2{7/9}5]
1𝑋77 7𝑋2𝑋76 7𝑋6 4.75
= 1-[ + + . ]
97 97 2 97
76
= 1- [7+14+12] = 1- 0.8117 = 0.1883
97

33 Prof. Balaram Pd. Sharma

EX.[9]. Out of 800 families with 4 children each, what percentage would be
expected to have (a). 2 boys and 2 girls (b). at least one boy (c). no girls (d). at
most 2 girls.

Solution: Here, N=800, n=4, probability of being a boy or success (p) = 1/2. And
q=1/2
(a). Probability of being 2 boys and 2 girls, P(r=2) =?
Now, P(r=2) or P(2) = C(4,2)[1/2]2[1/2]4-2 = 6.[1/16] = 3/8.
Expected % of being 2 boys &2 girls, f(2) = 100.P(2) =100x3/8 = 37.5%
(b). Probability of being at least one boy, P(r≥ 1) =?
Now, P(r≥ 1) =P(1)+P(2)+P(3)+P(4) = 1- P(0 ) = 1- C(4,0).[1/2]0.[1/2]4-0
= 1 – 1.1.[1/2]4 = 1- 1/16 = 15/16
Expected % of being at least 1 boy, f(r) = N.P(r) = 100.[15/16] = 93.75%
(c) & (d) solve yourself.

EX.[10]. Assuming that half the population is vegetarian so that the chance of an
individual being a vegetarian is 1/2 and assume that 100 investigators can take
sample of 10 individual to see whether they are vegetarians. How many
investigators would you expect to report that 3 people or less vegetarians.
Solution: Here, total number of investigators, N=100.
Number of trials or samples of investigators, n=10,
probability of a vegetarian, p = 1/2, & q= 1-p =1/2.
Probability of being 3 or less people is vegetarian, P(r≤3) = ?
Now, P(r≤3) = P(0)+P(1)+P(2)+P(3)
=C(10,0)[1/2]0[1/2]10+C(10,1)[1/2]1[1/2]9+C(10,2)[1/2]2[1/2]8+C(10,3)[1/2]3[1/2]7
176
=(1/2)10 [1 + 10 + 45 + 120] = = 0.1718
32 𝑋 32
Hence, expected number that 3 or more people being vegetarian,
f(r≤3) =N.P(r≤3) = 100X0.1718 = 17.18% ≈ 17%

EX.[11]. A hen of a certain breed lay eggs on 5 days a week on an average. Find
how many days during a season of 100 days a poultry keeper with 5 hens of these
breed, will expect to receive at least 4 eggs.

34 Prof. Balaram Pd. Sharma

Solution: Here, probability of a success (p) =5 days/7 days =5/7, q = 1-p =2/7, n=5,
Probability of getting at least 4 eggs, P(r≥ 4) = P(4)+P(5) = C(5,4)p4q1+C(5,5)p5q0
5 2 5 55
= 5.[ ]4 . + 1. [ ]5 . 1 = [2 + 1] = 0.5578
7 7 7 75
Finally, the expected number of days, f(r≥4) = N.P(r≥ 4) = 100x0.5578
= 55.78 ≈ 56 days.

N0te: Expected % is not necessary to express in nearest integer. But the expected
number or value or frequency always should be expressed in nearest integer.

EX.[12]. In a box containing 60 bulbs, 6 are defective. What is the probability that
out of a sample of 5 bulbs (a). none is defective. (b). exactly 2 are defective.
[solve!]

Ex.[13]. In a box containing 90 screws, 27 are defective. What is the probability

that out of a sample of 6 screws, all are defective. [solve!]

Ex.[14]. A dice is thrown 6 times. Getting an even number is a success. What is

the probability of getting (a). 5 success. (b). at least 5 success. (c). at most 5
success. [solve!]

Ex. [15]. Five coins are tossed 3200 times. Fit a binomial distribution to the
following data assuming the coin is unbiased.

Number of heads : 0 1 2 3 4 5
Frequency : 90 560 1000 900 600 50
Solution: Here, n=5, N=𝛴f=3200, p=1/2, and q=1-p=1-1/2=1/2.
By binomial probability distribution, the expected frequency of r heads out of 5 in
3200 trial is,
f(r) = N.P(r) = N. C(n,r) prqn-r = N.C(5,r)[1/2]r.[1/2]5-r
1
∴ f(r) =3200.C(5,r). =100.C(5,r). … … … … ….[i]
25

Fitting of binomial distribution

R Probability distribution P(r) Expected frequency distribution

f(r)=100.C(5,r)
r=0 C(5,0).[1/2]0 .[1/2]5 =1/32 100.C(5,0) = 100

35 Prof. Balaram Pd. Sharma

1 C(5,0).[1/2]1.[1/2]4 =5/32 100.C(5,1) = 500
2. 3
2 C(5,0).[1/2] [1/2] =10/32 100.C(5,2) = 1000
3. 2
3 C(5,0).[1/2] [1/2] =10/32 100.C(5,3) = 1000
4. 1
4 C(5,0).[1/2] [1/2] =5/32 100.C(5,4) = 500
5. 0
5 C(5,0).[1/2] [1/2] =1/32 100.C(5,5) = 100
EX.[16]. One hundred and ninety two families (for each of which the possibility of
an albino child being born is otherwise established.) had the following distribution
of albinos among the first three children.

Number of children: 0 1 2 3 Total

Number of families: 77 90 20 5 192
Find the expected frequencies on the basis of the theoretical probability 0.25of a
child being an albino.

Solution: Here, n=3, number of families N=𝛴f=192, P=0.25=1/4,q=0.75=3/4

By binomial distribution, the expected frequency of r child being albino birth out
of 3 in N=192 families is, f(r) = N.P(r) = N.C(n,r).pr.qn-r
1
= 192.C(3,r).[1/4]r.[3/4]3-r =192.C(3,r).33-r.
43
3-r 4-r
∴ f(r) =3.C(3,r).3 = C(3,r).3 … … … … ….[i]

Fitting of binomial distribution

R Probability distribution P(r) Expected frequency distribution f(r)

0 C(3,0)[1/4]0.[3/4]3 = 27/64 C(3,0).34-0 = 81
1 C(3,0)[1/4]1.[3/4]2 = 27/64 C(3,0).34-1 = 81
2 C(3,0)[1/4]2.[3/4]1 = 9/64 C(3,0).34-2 = 27
3 C(3,0)[1/4]3.[3/4]0 = 1/64 C(3,0).34-3 = 3
Total 𝛴P(r) = 1 𝛴f(r) = 192.

EX.[17]. Fit the binomial distribution and find the expected frequencies to the
following data:

Variable X : 0 1 2 3 4 Total
Frequency f : 28 62 46 10 4 150
Solution: Here, n =4, N=𝛴f =150, if p be the parameter of binomial distribution.
Where, p be the probability of success.
36 Prof. Balaram Pd. Sharma
 ∑ 𝑓𝑥 0 𝑋 28+1 𝑋 62+2 𝑋 46+3 𝑋 10+4 𝑋 4
Now, pn = 𝑋̅ = = =200/150 =4/3
𝑁 150
∴ 𝑝 =4/[3x4] =1/3, &q =1-p =2/3.
By binomial probability distribution, the expected frequencies are given by,
f(r) = N.P(r) =150.C(n,r)pr.qn-r = 150. C(4,r).[1/3]r.[2/3]4-r
∴f(r) = 150. C(4,r).1/[3]4.24-r
= = C(4,r).24-r.[50/27]………………………….….[i]

Fitting of binomial distribution:

R Probability distribution P(r) Expected frequency distribution f(r).

0 4
0 C(4,0).[1/3] .[2/3] C(4,0).24-0.[50/27] =29.63 ≈30
1 C(4,0).[1/3]1.[2/3]3 C(4,0).24-1.[50/27] =59.25 ≈30
2 C(4,0).[1/3]2.[2/3]2 C(4,0).24-2.[50/27] =44.44 ≈30
3 C(4,0).[1/3]3.[2/3]1 C(4,0).24-3.[50/27] =14.81 ≈30
4 C(4,0).[1/3]4.[2/3]0 C(4,0).24-4.[50/27] =1.851 ≈30
Total 𝛴P(x) = 1. 𝛴f(x) = 150.
EX.[18]. Fit a binomial distribution to the following data:

Variable X : 0 1 2 3 4 Total
Frequency f : 10 25 30 20 15 100
[solve it!]

MULTINOMIAL DITRIBUTION:

Multinomial distribution is the generalization of the binomial distribution. The

assumption of multinomial distribution are as follows:

• An experiment is performed under the same conditions for a fixed number

of trial, say ‘n’.
• There are ‘k’ number of mutually exclusive and exhaustive outcomes of the
experiment which are referred to sample spaces as; S={E1, E2, E3,…… …,Ek}
• The respective probabilities of events E1, E2, E3,…… …,Ek are p1, p2, p3, … …
…,pk respectively where, p1+ p2+ p3+ … … …+pk =1
• The trials are independent.

37 Prof. Balaram Pd. Sharma

Note: the probability that there will be r1 occurrence of E1, r2 occurrence of
E2………….; rk occurrence of Ek in n trials are given by,
𝑛!
P(r1 r2 r3………rk) = .𝑝1 𝑟1 . 𝑝2 𝑟2 … . . 𝑝𝑘 𝑟𝑘
𝑟1 !.𝑟2 !…..𝑟𝑘 !

Where, r1+r2+r3+………+rk=n, and p1+ p2+ p3+ … … …+pk =1.

Worked out examples:

EX.[1]. A community consists of 50% Hindus, 30% Sikhs, and 20% Muslim. If a
sample of 6 individual is selected at random, what is the probability that two are
Hindus, three are Sikhs and only one is Muslim.

Solution: the problem is of type multinomial distribution.

Here, p1=0.5, p2=0.30, p3=0.20, r1=2, r2=3, and r3=1
Again, r1+r2+r3 =n=6 and p1+ p2+ p3 =1

By using the formula for multinomial distribution, required probability is,

𝑛!
P(r1 r2 r3) = .𝑝1 𝑟1 . 𝑝2 𝑟2 . 𝑝3 𝑟3
𝑟1 !.𝑟2 !.𝑟3 !

6!
= [0.5]2 . [0.3]3 . [0.2]1 = 0.081
2!.3!.1!

EX.[2]. A dice is rolled 5 times. Find the probability of getting one a1, one a2 and
three other numbers.

Solution: the multinomial distribution model is applicable for this problem.

Here, p1=1/6, p2=1/6, p3=4/6=2/3, r1=1, r2=1, and r3=3
Again, r1+r2+r3 =n=5 and p1+ p2+ p3 =1

By using the formula for multinomial distribution, required probability is,

𝑛!
P(r1 r2 r3) = .𝑝1 𝑟1 . 𝑝2 𝑟2 . 𝑝3 𝑟3
𝑟1 !.𝑟2 !.𝑟3 !

5!
= [1/6]1 . [1/6]1 . [2/3]3 = 40/243 =0.165
1!.1!.3!

38 Prof. Balaram Pd. Sharma

POISSON DITRIBUTION :

Poisson distribution is considered as the limiting case of the binomial probability

distribution under the following conditions:

• The number of trials ‘n’ is indefinitely large. In this case n → ∞

• The probability of success p for each trial is sufficiently small. So, p→0.
• The number ‘np’ is a finite number, say, m. then m=np.

Let X be the discrete random variable. Also, m [=np] be the mean of the Poisson
distribution. Then the probability function of Poisson distribution is given by,
𝑒 −𝑚 .𝑚𝑟
P(X=r) = ….. ……… ……..[i]
𝑟!

Where, r= 0, 1, 2, 3,…. Non-negative whole number which is the no. of success

m= mean of the distribution = np.
e = base of the natural logarithm. The value of e = 2.71828.

Note that the Poisson distribution can be obtained, if the value of mean m or np is
known.

Properties of Poisson distribution:

• Poisson distribution is discrete probability distribution.

• The parameter of Poisson distribution is the mean ‘m’ or ‘np’.
• Poisson distribution is independent of number of trials ‘n’
• The mean, variance and standard deviation of the Poisson distribution are
given by, mean (𝑋̅) = m, variance (𝜎 2 ) =m, standard deviation(σ) = √𝑚.

Fitting of Poisson distribution: the Poisson distribution for different values of r is

𝑒 −𝑚 .𝑚𝑟
calculated as; P(X=r) =
𝑟!

Where, r= 0, 1, 2, 3,…. Non-negative whole number which is the no. of success

m= mean of the distribution = np.

39 Prof. Balaram Pd. Sharma

If N be the total observed frequency, then the expected or theoretical
frequencies of the Poisson distribution is,
𝑒 −𝑚 .𝑚𝑟
f(r) = N.P(r). =N. ,
𝑟!
particularly,
𝑒 −𝑚 .𝑚0 𝑒 −𝑚 .𝑚1
f(0) = N.P(0) =N. = N.e-m , f(1) = N.P(1) =N. = Nm.e-m.
0! 1!
𝑒 −𝑚 .𝑚2 𝑒 −𝑚 .𝑚3
f(2) = N.P(2) =N. = Nm2.e-m , f(3) = N.P(3) =N. = Nm3.e-m.
2! 3!

Worked out Examples:

Ex.[1].(a). The standard deviation of a Poisson distribution is 2 .Find the

probability corresponding to the variable X=3. (given, e-4=0.0183).
(b). If X be the Poisson variable with parameter 1.Find P(3<x<5).
(given, e-1=0.36783).

Solution: (a). Here, standard deviation of the Poisson distribution, 𝜎𝑥 =2. So

mean ‘m’ = variance =𝜎𝑥2 =4. Now, P(X=3) =?
𝑒 −𝑚 .𝑚𝑟 𝑒 −4 .43
By Poisson distribution, P(X=r=3) or P(3) = =
𝑟! 3!
= 0.0183 x [64/6] =0.1952

(b). Here mean of the Poisson distribution, ‘m’ = 1, P(3<X<5) =?

By the formula of Poisson distribution, P(3<X<5) = P(4)
𝑒 −𝑚 .𝑚𝑟 𝑒 −1.14
= = = e-1/24 = 0.0153
𝑟! 4!

EX.[2]. A manufacturer of pins knows that on an average 2% in production is

defective. He sells pin in boxes of 100 and guarantee that not more than 2 pins
will be defective. What is the probability that a box randomly selected
(a) will meet the guarantee quality. (b) will not meet the guarantee quality.

Solution: Here, p=2/100, n=100,

parameter of Poisson distribution, mean ‘m’= [2/100].100 = 2
(a). Probability that selected box will meet guarantee quality, P(X<2) =? Now,
𝑒 −2 .20 𝑒 −2 .21 𝑒 −2.22
P(X<2) = P(0)+P(1)+P(2) = + +
0! 1! 2!

40 Prof. Balaram Pd. Sharma

 =e-2[1+2+2] = 0.1353 x 5 = 0.6765

(b). Probability that the selected box will not meet the guarantee quality,
P(X>2) =? Now, P(X>2) =1- P(X≤2) = 1- 0.6765 = 0.3235

EX.[3]. Find the probability that at most 5 defective bolts will be found in a box
of 200 bolts. If it is known that 2% of such bolts are expected to be defective.
You may take the distribution to be Poisson. Take e-4 = 0.0183

Solution: Here, n =200, p=2/100,

parameter of Poisson distribution, mean (m)=pn = 200x[2/100]=4.
Probability of at most 5 defective, P(X≤ 5) =?
Now, P(X≤5)= P(0)+P(1)+P(2)+P(3)+P(4)+P(5)
𝒆−𝟒 .𝟒𝟎 𝒆−𝟒 .𝟒𝟏 𝒆−𝟒 .𝟒𝟐 𝒆−𝟒 .𝟒𝟑 𝒆−𝟒 .𝟒𝟒 𝒆−𝟒 .𝟒𝟓
= + + + + +
𝟎! 𝟏! 𝟐! 𝟑! 𝟒! 𝟓!

=e-4[1 + 4 + 8 + 32/3 + 32/3 + 128/15]

=0.0183 x 42.88 = 0.7846

EX.[4]. An automatic machine makes paper clips from coils of wire on an average
1 in 400 paper clips, is defective. If the paper clips are packed in boxes of 100,
What % of the boxes of clips contains (a).no defective. (b). one or more defective.
(c). less than 2 defective.

Solution: Here, n=100, p=1/400,

Poisson’s parameter ‘mean’ m=np=[1/400].100=0.25
(a). Percentage of the box of clips contains no defective =100 x P(0)
𝑒 −0.25 .0.250
=100. =100 x 0.7787 = 77.87%
0!

(b). Percentage of box containing one or more clips defective = 100 x P(X≥1)
=100.[1- P(0)] = 100.[1- 0.7787] {from part (a) }

=100 x 0.2213 = 22.13%

41 Prof. Balaram Pd. Sharma

(c). Percentage of box containing less than 2 defective. =100 x P(X<2)
𝑒 −0.25 .(−0.25)0 𝑒 −0.25 .(−0.25)1
= 100.[P(0)+P(1)] = 100.[ + ]
0! 1!
= 100 x e-0.25[1+0.25] = 100 x 0.7787 x 1.25 = 97.34%

EX.[5]. In a certain factory turning out optical lenses, there is a small chance
1/500 for any one lens to be defective. The lenses are supplied in packet of
10.Use Poisson distribution to calculate the approximate number of packets
containing (a). no defective. (b).one defective. (c). 2 defective. (d). at least 3
defective lenses respectively in a consignment of 20,000 packets.
(given, e-0.02=0.9802).

Solution: Here, number of lenses in a packet, ‘n’ =10, p=1/500.

Poisson parameter (mean), ‘m’=np =10.[1/500] =0.02 , N =20,000.
(a). Approximate number of packets containing no defective, f(0) =?
𝑒 −𝑚 .𝑚𝑟
Now, Poisson distribution, P(0) = =e-0.02 .[0.02]0 = 0.9802
𝑟!
Hence, approximate no. of packets, f(0) = N.P(0) =20,000 x 0.9802 =19604.
(b) . Approximate number of packets containing one defective, f(1) =?
𝑒 −𝑚 .𝑚𝑟
Now, Poisson distribution, P(1) = =e-0.02 .[0.02]1 = 0.019604
𝑟!
Hence, approximate no. of packets, f(0)
= N.P(0) =20,000 x 0.019604 =392.08 ≈ 392.

(c). Approximate number of packets containing 2 defective, f(2) =?

𝑒 −𝑚 .𝑚𝑟
Now, Poisson distribution, P(2) = =e-0.02 .[0.02]2 .[1/2!] = 0.00019604
𝑟!
Hence, approximate no. of packets, f(2) = N.P(2)
= 20,000 x 0.00019604 =3.920 ≈ 4

(d). Approximate number of packets containing at least 3 defective, f(X≥ 3) =?

Now, Poisson distribution, P(X≥ 3) = 1- P(X<3) = 1-[P(0)+P(1)+P(2)]
= 1 - [0.9802+0.019604+0.00019604] = 1-1.00000004 ≈ 0
Hence, approximate no. of packets, f(X≥ 3) = N. P(X≥ 3) ≈ 0

42 Prof. Balaram Pd. Sharma

EX.[6]. A systematic sample of 200 pages was taken from the manuscript typed by
a typist and observed frequency distribution of the typing mistakes per page was
found to be as follows:

Number of typing mistakes [X]: 0 1 2 3 4

Number of pages [f] : 122 60 15 2 1

Fit the appropriate frequency distribution to the above data.

Solution: fitting of Poisson distribution.

X F fX
0 122 0
1 60 60
2 15 30
3 2 6
4 1 4
Total 𝛴f =200. 𝛴fX =100
Mean 𝑋̅ = 𝛴fX/N = 100/200 = 0.5 By Poisson probability distribution, the
theoretical or expected frequencies are as given below;
𝑒 −𝑚 .(𝑚)𝑟
f (r) = N.P(r) = N. ... … … …[i]
𝑟!
where, r=0, 1, 2, 3, 4. Substituting the values of r in [i], we get the respective
theoretical or expected frequencies are as follows:

Calculation of expected (or theoretical) frequencies

r 𝒆−𝒎 .(𝒎)𝒓 Expected (theo.)freq. dist., f(r)=N.P(r)

Probability distrib.,P(r)=
𝒓!
0 [1/0!].𝑒 −0.5 . [0.5]0 = 0.60650 200 x 0.60650 = 121.300 ≈ 121
1 [1/1!].𝑒 −0.5 . [0.5]1 = 0.30325 200 x 0.30325 = 60.650 ≈ 61
2 [1/2!].𝑒 −0.5 . [0.5]2 = 0.07810 200 x 0.07810 = 15.1625 ≈ 15
3 [1/3!].𝑒 −0.5 . [0.5]3 = 0.01263 200 x 0.01263 = 2.5270 ≈3
4 [1/4!].𝑒 −0.5 . [0.5]4 = 0.00157 200 x 0.00157 = 0.3158 ≈0
Total 𝛴P(r) ≈ 1 𝛴f(r) = 200 = N

43 Prof. Balaram Pd. Sharma

EX.[7]. The following table gives the number of deaths in 186 days period in a
certain part of a city. Fit the Poisson distribution to the data:

Number of deaths [X]: 0 1 2 3 4 total

Number of days [f] : 120 58 5 2 1 86.

Solution: Fitting of Poisson distribution.

Number of deaths (X) Number of days (f) fX

0 120 0
1 58 58
2 5 10
3 2 6
4 1 4
Total 𝛴f =N = 186. 𝛴fX = 78.
.The parameter of the Poisson distribution, ’mean’ (𝑋̅) = 𝛴fX/N = 78/186 = 0.4193.
By using Poisson probability distribution, the theoretical or expected frequencies
𝑒 −𝑚 .𝑚𝑟
are as follows; f(r) = N.P(r) = N. … … … … …[i]
𝑟!
where r = 0, 1, 2, 3, 4. Substituting the values of r successively in [i], we get the
expected or theoretical frequencies as;

Calculation of expected or theoretical frequencies

r Probability distribution, Expected (theo.)freq. dist., f(r)=N.P(r)

𝒆−𝒎 .(𝒎)𝒓
P(r)=
𝒓!
0 [1/0!].e-0.4193.[0.4193]0 = 0.6575 186 x 0.6575 = 122.29 ≈ 122
1 [1/1!].e-0.4193.[0.4193]1 = 0.2756 186 x 0.2756 = 51.278 ≈ 51
2 [1/2!].e-0.4193.[0.4193]2 = 0.0577 186 x 0.0577 = 10.75 ≈ 11
3 [1/3!].e-0.4193.[0.4193]3 = 0.00807 186 x 0.00807 = 1.5025 ≈ 2
4 [1/4!].e-0.4193.[0.4193]4 = 0.00084 186 x 0.000846 =0.1575 ≈ 0
total 𝛴P(r) ≈ 1 𝛴f(r) = N =186.

EX. [8]. Fit a Poisson distribution to the following data and calculate the expected
(or theoretical) frequencies. Also compute the mean and variance of the fitted
distribution:

44 Prof. Balaram Pd. Sharma

X: 0 1 2 3 4 total. .
f: 123 59 14 3 1 200. [solve it!]

EX.[9]. 1582 drivers were being asked how many accidents they had caused. 951
had caused no accident, 501 had caused only one accident, 100 had caused 2
accidents and 30 had caused 3 accidents each. Which distribution is appropriate
for these data and why? Also fit the distribution. [HINTS: The case is Poisson
distribution because the number of trials ‘n’ is very large which is 1582 in number]
[solve it!.]

NORMAL DISTRIBUTION

If X be a continuous random variable following probability distribution with mean

𝜇 (-∞ < 𝜇 < ∞) and standard deviation 𝜎 (𝜎 > 0), 𝑡ℎ𝑒𝑛 probability density
function (P.D.F) is given by the relation,

Note that the parameters of the normal distribution are 𝜇 𝑎𝑛𝑑 𝜎.

The graph of the normal distribution is “bell shapped” curve.

45 Prof. Balaram Pd. Sharma
Notes:

1.The total area under the normal probability curve P(x) is equal to 1.

2. The normal distribution can have different shapes on the basis of values of 𝜇 𝑎𝑛𝑑 𝜎 .And
there is unique normal distribution corresponding to pair (𝜇, 𝜎).

3. Two tails of normal probability distribution extend indefinitely and never touch the
horizontal axis.

4.The mean of normally distributed population lies at the centre of its normal curve.

5.Given 𝜇 𝑎𝑛𝑑𝜎 as parameters, the probability of a random variable X which is normally

distributed between two specified x=a and x=b is.

P(a<X<b) = Area under the curve P(X) between x=a and x=b.

Standard normal distribution:

The normal probability curve with mean 𝜇 and standard deviation 𝜎 is given that
−1
1 𝑋−𝜇 2
P(X) = 𝜎√2𝜋 . 𝑒 2 . [ ] ………………………………………….[1]
𝜎

Where, -∞ < 𝑋 < ∞

𝑋−𝜇
If the nomal variate X is changed into standaed normal variate z [where, z = ]. Then, the
𝜎
standard normal distribution or z-distribution is given by,
−1
1
P(Z) = 𝜎√2𝜋 . 𝑒 2 𝑧 2 ………………………………………….[2]

Where, -∞ < 𝑧 < ∞

Characteristics of standard normal distribution:

The main characteristics of standard normal distribution and normal curve are as follows:

1. The curve is bell - shapped and symmetrical about mean 𝜇.

2, Mean, median and mode coincide, since the distribution is symmetrical. So, 𝜇 = Md = Mo .

46 Prof. Balaram Pd. Sharma

3. The ordinate X = 𝜇 (I,e,Z=0) divides the whole area in two equal parts.The area towards right
and left part of X=𝜇 are both equal to 0.5

4. The normal curve has only one peak. So the distribution is unimodal.

5. Mathematically, asymptotic behavior of the normal curve exists, since both tails extend

Indefinitely and never touch horizontal line.

6. Skewness is zero. i.e. 𝛽1 = 𝛾1 = 0 and the curve is mesokurtic. i.e., 𝛽2 = 3 𝑎𝑛𝑑 𝛾2 = 0

7. Being symmetric, 𝑄3 + 𝑄1 = 2. 𝑀𝑑 .

8. The area under the normal probability curve between the ordinate at X=𝜇 − 𝜎 and X=𝜇 + 𝜎

Is 0.6826 ,Then, Prob (𝜇 − 𝜎 < 𝑋 < 𝜇 + 𝜎) =0.6826.

Prob (𝜇 − 2𝜎 < 𝑋 < 𝜇 + 2𝜎) =0.9544.

And, Prob (𝜇 − 3𝜎 < 𝑋 < 𝜇 + 3𝜎) =0.9973.

𝑋−𝜇
9. SinceType equation here., Z= ,When,X=𝜇 ± 𝜎 𝑡ℎ𝑒𝑛, 𝑍 = ±1
𝜎

When,X=𝜇 ± 2𝜎 𝑡ℎ𝑒𝑛, 𝑍 = ±2

And, When,X=𝜇 ± 3𝜎 𝑡ℎ𝑒𝑛, 𝑍 = ±3

New version,

X Z % coverage of area
𝜇 ± 1.64𝜎 ±1.64 90%
𝜇 ± 1.96𝜎 ±1.96 95%
𝜇 ± 2.58𝜎 ±2.58 99%

Example worked out:

[1]. Find the area under the normal curve

(a).between Z=0 and Z=1.78 (b). between Z=-0.85 and Z=0

(c).between Z=0.85 and Z=1.65 (d). between Z=-0.75 and Z=0.20

(e).between Z=-0.9 and Z=1.62 (f). left of Z=1.25

(g).right of Z=1.25

47 Prof. Balaram Pd. Sharma

Solution:

(a).Area between Z=0 and Z=1.78. i.e.

P(0<Z<1.78) =?

By table, P(0<Z<1.78)=0.4625

(b). Area between Z=-0.85 and Z=0

i.e.P(-o.85<Z<0)=?

We have, P(-0.85<Z<0)=P(0<Z<0.85)

=0.3023 [By table]

(c). Area between Z=0.85 and Z=1.65

i.e.P(o.85<Z<1.65)=?

We have,
P(0.85<Z<1.65)=P(0<Z<1.65)-
P(0<Z<0.85)

=0.4505-0.3023 [By table]

=0.1482

(d). Area between Z=-0.75 and Z=0.20

i.e.P(-o.75<Z<-0.20)=?

We have, P(-0.75<Z<-
0.20)=P(0.20<Z<0.75)

=P(0<Z<0.75)-P(0<Z<0.20)

48 Prof. Balaram Pd. Sharma

=0.2734-0.0791 [By table]

=0.194

(e). Area between Z=-0.9 and Z=1.62

i.e.P(-o.9<Z<1.62)=?

We have, P(-0.9<Z<1.62)=P(-
0.9<Z<0)+P(0<Z<1.62)

=P(0<Z<0.9)+P(0<Z<1.62)

=0.3159+0.4474 [By table]

=0.7633

(f). Area left of Z=1.25

i.e.P(Z<1.25)=?

We have, P(Z<1.25)= P(-∞ < 𝑍 < 0) +P(0<Z<1.25)

=0.5+0.3944 [By table]

=0.8944

(g). Area right of Z=1.25

i.e.P(1.25<Z)=?

We have, P(1.25<Z)= P(0< 𝑍 < ∞) −P(0<Z<1.25)

=0.5-0.3944 [By table]

=0.1056

[2].A company manufactures crome and glass lamp. It requires on an average of 40 labour
hours to complete on with a standard deviation of 10 hours. (i).what is the probability that it
will take between 35 and 42 labour hour to complete one of the lamp. (ii). What is the

49 Prof. Balaram Pd. Sharma

probability that it will take more than 48 hours? [Given, Z0.2 = 0.0793, Z0.5 = 0.1815, Z0.8 =
0.2881]

Solution: Let X denotes the random variable and Z denotes the standard normal variables.

Here, Mean (𝜇) = 40 labour hours.

Standard deviation (𝜎) =10 labour hours.

(i). P(35<X<42) = ? (ii). P(X>48) = ?

𝑋−𝜇
Since the standard normal variable , Z = ,
𝜎

When X1 = 35 hours, then, Z1 = (35-40)/10 = -0.5

When, X2 = 42 hours, then Z2 = (42-40)/10 = 0.2

Now,P(35<X<42) = P(-0.5<Z<0.2)

=P(-0.5<Z<0) + P(0<Z<0.2)

=P(0<Z<0.5) + P(0<Z<0.2)

= 0.1915 + 0.0793 [By given value]

=0.2708

(ii). Probability that production will takes more than 48 hours, P(X>48) = ?

When, X = 48, then, Z = (X-𝜇)/𝜎 = (48-40)/10 = 0.8

Now, P(X>48) = P(Z>0.8) = P(0<Z<∞) - P(0<Z<0.8)

= 0.5 – 0.2881

= 0.2119

[3]. The mean life of a certain type of electric bulbs is 1200 hours and standard deviation is 300
hours. Assuming the data is to be normally distributed. What percent of the electric bulbs are
expected to have life (i). more than 1500 hours. (ii). Between 1000 and 1400 hours. (iii). Less
than 600 hours. (iv). More than 600 hours

Solution: LetX denotes the life of an electric bulbs and Z denote the standard normal variable.
Here, Mean (𝜇) = 1200 hours, Standard deviation (𝜎) = 300 hours.
𝑋− 𝜇
Now, Standard normal variate, Z = = (X – 1200)/300.
𝜎

50 Prof. Balaram Pd. Sharma

When X = 1500 hours. Then, Z = (1500 – 1200)/300 = 1

When, X = 1000hours, then, Z = (1000 – 1200)/300 = -0.67

When, X = 1400 hours, then Z = (1400 – 1200)/300 = 0.67

When, X = 600 hours, then, Z = (600 – 1200)/300 = -2

(i). Prob. of life more than 1500 hours i.e. P(X>1500) = P(Z>1)

=P(0<Z<∞) - P(0<Z<1)

=0.5 – 0.3413 = 0.1587

Hence, percentage of electric bulbs having life more than 1500 hours = 15.87%

(ii). Probability of electric bulbs having life between 1000 to 1400 hours

P(1000<X<1400) = P( -0.67<Z<0.67)

=P( -0.67<Z<0) + P(0<Z<0.67)

=P(0<Z<0.67) + P(0<Z<0.67)

= 0.2486 + 0.2486 = 0.4972

Hence, Percentage of electric bulbs having life between 1000 to 1400 hours = 49.72%

(iii).Probability of bulbs having life less than 600 hours, P(X<600) = P(Z< -2)

= P( -∞ < 𝑍 < 0) - P( -2<Z<0)

= 0.5 – P(0<Z<2)

=0.5 - 0.4772 = 0.0228

Hence, .Percentage of bulbs having life less than 600 hours = 2.28%

(iv). Probability of bulbs having life more than 600 hours, P(X>600) = P(Z> -2)

= 1 – P(Z< -2)

= 1 – 0.0228 = 0.9772

Hence, percentage of bulbs having life more than 600 hours = 97.72%

51 Prof. Balaram Pd. Sharma

[4]. The mean height of soldiers to be 68.52 inches with a variance 10.8 inches.How many
soldiers in a regiment of 1000 would you expect over 6 feet tall?

Solution: Let X denote the height of soldiers and Z denote the standard normal variables.

Here, Mean height of soldiers (𝜇) = 68.52 inches.

Variance (𝜎 2 ) = 10.8 inches. So, standard deviation (𝜎) = 3.29 inches.

Number of soldiers (N) = 1000.

Now the standard normal variate, Z = (X –𝜇)/𝜎 = (X -68.52)/3.29

When, X = 6 ft = 72 inches, then Z = (72 – 68.52)/3.29 = 1.06

The probability of soldiers over 6 ft. = P(X>6 ft.) = P(Z>1.06)

=P(0<Z<∞) – P(0<Z<1.06)

=0.5 – 0.3554 = 0.1446

Finally expected number of soldiers over 6 ft. = N. P(X>6 ft.)

=1000 . (0.1446)

=144.6 ≈ 145 (Nearly)

[5]. A banker claims that the life of a regular sving account opened in his bank averages 18
m0nths with a S.D. of 6.45 months. What is the probability that

(i) there will be money in account between 20 to 22 months by a depositors.

(ii) the account will be closed after 2 years.

[Given that Z 0.3 = 0.1217, Z 0.62 = 0.2324, Z 0.93 = 0.3238]

Solution: Let X denotes the random variable of no. of months for which the account is running.
Z be the standard normal variables.

Here, Mean (𝜇) = 18 m0nths., S.D. (𝜎) = 6.45 months.

Standard normal variate Z = (X – 𝜇)/𝜎 = (X – 18)/6.45

When X = 20 months, then Z = 0.31, When X = 22 months, then Z = 0.62

When X =24 months, then Z = 0.93

52 Prof. Balaram Pd. Sharma

(i). Probability that the account consists of money 20 to 2 months.

P(20<X<22) = P(0.31<Z<0.62) = P(0<Z<0.62) – P(0<Z<0.31)

=0.2324 – 0.1217 = 0.1107

(ii). Probability that the account will be closed after 2 years ( = 24 months.)

P(X>24) = P(Z>0.93) = P(0<Z<∞) – P(0<Z<0.93)

=0.5 – 0.3238 = 0.1762

[6]. A sample of 1000 dry battery cells to find the length of life produced the following results
𝜇 = 12 ℎ𝑜𝑢𝑟𝑠. 𝜎 = 3 ℎ𝑜𝑢𝑟𝑠. Assume the data to be normally distributed.What percentage of
the battery cells are expected to have life (i). more than 15 hours. (ii). Less than 6 hours. (iii)
between 10 hours and 14 hours. Given,

Z 2.5 2 1 0.67
Area 0.4938 0.4772 0.3413 0.2486
Solution: Let X denotes the random variable of life of the dry battery cells and Z that of
standard normal variables.

Here, mean (𝜇) = 12 hours, S.D. (𝜎) = 3 hours, N = 1000.

Now, the standard normal variable, Z = (X – 𝜇)/𝜎 = (X – 12)/3

When, X = 6 hours, then Z = - 2, When, X = 15 hours, then Z = 1

When, X = 10 hours, then Z = - 0.67, When, X = 14 hours, then Z = 0.67

(i). Probability of life more than 15 hrs., P(X>15) = P(Z>1)

= P(0<Z<∞) – P(0<Z<1)

= 0.5 – 0.3413 = 0.1587

Hence, expected % of the life more than 15 hrs. = 100 . (0.1587) = 15.87%

(ii). Probability of life less than 6 hrs., P(X<6) = P(Z< - 2)

= P(-∞<Z<0) – P(-2<Z<0) = 0.5 – P(0<Z<2)

= 0.5 – 0.4772 = 0.0228

Hence, expected % of the life less than 6 hrs. = 100 . (0.0228)% = 2.28%

53 Prof. Balaram Pd. Sharma

(iii). Probability of life between 10 hrs.and 14hrs, P(10<X<14)

=P( -0.67<Z <0.67)

= P( -0.67<Z<0) + P(0<Z<0.67)

=P(0<Z<0.67) + P(0<Z<0.67)

= 0.2486 + 0.2486 = 0.4972

Hence, expected % of the life between 10 hrs. and 14 hrs. = 100 . (0.4972)% = 49.72%

[7]. The average daily sales of 500 branch offices was Rs.150 thousand and S.D. Rs.15 thousand.
Assuming the distribution to be normal. How many branches have sales between

(i). Rs.120 thousand and 145 thousand. (ii). Rs.140 thousand and 165 thousand.

Solution: Let X be the random variable of daily sale and Z be standard normal variable.

Here, N = no. of branches =500, Mean (𝜇) = Rs.150 thousand, s.d.(𝜎) = Rs. 15 thousand.

Also, standard normal variable, Z = (X – 𝜇)/𝜎 = (X – 150)/15

When, X = 120 thousand,then Z = -2, When, X = 140 thousand,then Z = -0.67

When, X = 145 thousand,then Z = -0.33, When, X = 165 thousand,then Z = 1

(i). Prob. that the sales between Rs.120 thousand and Rs. 145 thousand,

P(120<X<145) = P( -2<Z< -0.33)

=P( -2<Z<0) – P( -0.33<Z<0) = P(0<Z<2) – P(0<Z< 0.33)

=0.4772 – 0.1293 = 0.3479

Hence, expected no. of branches having sales between Rs.120 thousand and Rs. 145 thousand,

= N. (0.3479) =500 X 0.3479 = 173.95≈ 174 [Nearly]

(ii). Prob. that the sales between Rs.140 thousand and Rs. 165 thousand,

54 Prof. Balaram Pd. Sharma

 P(140<X<165) = P( -0.67<Z< 1)

=P( -0.67<Z<0) + P( 0<Z<1) = P(0<Z<0.67) + P(0<Z< 1)

=0.2486 + 0.3413 = 0.5899

Hence, expected no. of branches having sales between Rs.140 thousand and Rs. 165 thousand,

= N. (0.5899) =500 X 0.5899 = 294.95≈ 295 [Nearly]

[8]. The income of a group of 10,000 persons was found to be normally distributed with mean
Rs.750 per month and s. d. Rs. 50. Find the expected no. of persons with income (i) less than
Rs.700 per month. (ii) between Rs. 700 and 800 per month.

Solution: Let X denotes the random variable of income and Z denotes the standard normal
variate.

Here, 𝜇 = Rs. 750 per month, 𝜎 = Rs. 50 per month, No. of Persons N = 10,000.

The standard normal variable Z = (X -750)/50.

When, X = Rs. 700, then Z = -1, When, X = Rs. 800, then Z = 1,

(i).Prob. of income less than Rs. 700, P(X<700) = P(Z< -1)

= P( -∞<Z<0) – P( -1<Z<0) = 0.5 – P(0<Z<1)

=0.5 – 0.3413 = 0.1587

Hence, expected no. of persons having income less than Rs. 700

= N X P(X<700) = 10,000 X 0.1587 = 1587.

(ii).Prob. of income between Rs. 700 and 800, P(700<X<800) = P(-1<Z< 1)

= P( -1<Z<0) + P(0<Z<1) = P(0<Z<1)+ P(0<Z<1)

=0.3413 + 0.3413 = 0.6826

55 Prof. Balaram Pd. Sharma

Hence, expected no. of persons having income between Rs.700 and 800

= N X P(700<X<800) = 10,000 X 0.6826 = 6826.

[9]. The marks obtained by the students in an examination are known to be normally
distributed. If 10% of the students got less than 40 marks while 15% got over 80. What are the
mean and s.d. of the marks?

Solution: Let X be random variable of marks and Z be standard normal variable.𝜇 𝑎𝑛𝑑 𝜎 be
mean and s. d. of marks. Now, 𝜇 =? , 𝜎 =?

Here, P(X<40) = 0.10 and P(X>80) = 0.15

Standard normal variable Z = (X –𝜇)/𝜎

When X1 = 40, then Z = (40 – 𝜇)/𝜎 = -Z1 (Say)

When X2 = 80, then Z = (80 – 𝜇)/𝜎 = Z2 (Say)

Now, P(X<40) = 0.10 or, P(Z< -Z1) = 0.10

Or, P( -∞<Z<0) – P( -Z1<Z<0) = 0.10 or, 0.5 – P(0<Z<Z1) =0.10

Or, P(0<Z<Z1) = 0.4 Then, Z1 = 1.28 [by table]

Now, -Z1 = (40 – 𝜇)/𝜎 or, -1.28 = (40 – 𝜇)/𝜎

Then, 𝜇 − 1.28𝜎 = 40 ………………………………………….[1]

Also, P(X>80) =0.15 or, P(Z>Z 2) = 0.15

Or, P(0<Z<∞ ) – P(0<Z<Z2) = 0.15 or, 0.5 – 0.15 = P(0<Z<Z2)

Or, P(0<Z<Z2) = 0.35 then, Z 2 = 1.04 [by table]

Also, Z2 = (80 – 𝜇)/𝜎 or, 1.04 = (80 – 𝜇)/𝜎

Then, 𝜇 + 1.04𝜎 = 80 ………………………………………….[2]

56 Prof. Balaram Pd. Sharma

Solving [1] and [2] we get, 𝜇 = 62.07 and 𝜎 = 17.24

[10]. Income of a group of 10,000 persons was found to be normally distributed with mean
Rs.520 and s.d. Rs.60. Find: (i) the no. of persons having income between Rs. 400 and 550.

(ii). The lowest income of richest 1,000 persons. (iii) the highest income of poorest 1,000
persons.

Solution: Let X be random variable of income and Z be the standard normal variable.

Here, 𝜇 = 𝑅𝑠. 520, 𝜎 = Rs.60, N = 10,000.

(i)X1 = Rs.400, X2 = Rs.550, P(400<X<550) = ?

We have, Z = (X -520)/60, when X = 400, then Z = -2

and when Z = 550, then Z = 0.5

So, P(400<X<550) = P(0<Z<0.5)

= P( -2<Z<0) + P(0<Z<0.5)

= P(0<Z<2) + P(0<Z<0.5)

= 0.4772 + 0.1915

= 0.6687

Total no. of persons having income between Rs.400 and 550

= N X P(400<X<550) = 10,000 X 0.6687 = 6687

(ii) Let Z =Z1 be the standard normal variate value lowest income of richest 1000 people.

So, 1,000 = P(Z>Z1) X 10,000

Or, P(Z>Z1) = 1000/10.000 = 0.1

Or, P(0<Z<∞) – P(0<Z<Z1) = 0.1

57 Prof. Balaram Pd. Sharma

Or,0.5 – P(0<Z<Z1) = 0.1

Or, P(0<Z<Z1) = 0.5 – 0.1 = 0.4

Hence, Z1 = 1.28 [By table]

1.28 = (X – 𝜇)/𝜎 ∴X =𝜇 + 1.28𝜎 =520 + 1.28 X 60 =

596.8

Hence lowest income of 1,000 richest people = Rs.596.8

(iii) Let the standard normal value of highest income of poorest 1,000 persons is Z = -Z2.

Here, P(Z< -Z2) X 10,000 = 1,000

Or, P(Z< -Z2) = 1,000/10,000 = 0.1

Or,P( -∞<Z<0) – P( -Z2<Z<0) = 0.1

Or, 0.5 – P(0<Z<Z2) = 0.1

Or, P(0<Z<Z2) = 0.5 – 0.1 = 0.4 ∴Z2 = 1.28

Now, -Z2 = (X – 𝜇)/𝜎

-1.28 = (X – 𝜇)/𝜎

Then, X = 𝜇 − 1.28𝜎 = 520 – 1.28 X 60 = 443.2

[11].In an intelligence test, the admin tested to 1,000 students and found the average score
was 42 and s.d. 24. Find (a)the no. of students exceeding a scoreof 50 (b) the no. of students
having score lying between30 and 54. (c) the value of score exceeded by the top 100 students.

Solution: Let X be random variable of scores of intelligence test and Z be the standard normal
variable.

Here, N = 1000, 𝜇 = 42, 𝜎 = 24

(a) we have, Z = (X-42)/24 When X =50, then Z =0.33

58 Prof. Balaram Pd. Sharma

Now, prob. of student exceeding a score of 50, P(X>50) = P(Z>0.33)

=P(0<Z<∞) –P(0<Z<0.33) = 0.5 – 0.1293 = 0.3707

Hence, no. of students exceeding a score of 50 = N X P(X>50)

=1,000 X 0.3707 =370.7≈ 371 [Nearly]

(b). We have, Z = (X-42)/24 When X =30, then Z = -0.5

When, X =54, then Z = 0.5

Now, prob. of student having score between 30 and 54, P(30<X<54) = P( -0.5<Z<0.5)

=P(-0.5<Z<0) + P(0<Z<0.5) = 0.1915 +0.1915 = 0.3830

Hence, no. of students having score between 30 and 54 = N X P(30<X<54)

=1,000 X 0.3830 = 3830

(c).Let Z =Z1 be standard normal variable so that score of top 100 students exceeds by Z1.

Here, P(Z>Z1) = 100/1,000 = 0.1

Or, P(0<Z<∞ ) – P(0<Z<Z1) = 0.1

P(0<Z<Z1) = 0.5 – 0.1 = 0.4

Then, Z1 = 1.28 [by table]

But, 1.28 = (X -42)/24

So, X = 42 + 1.28 X 24 = 72.72

Hence, the value of score exceeded by the top 100 students = 72.72

[12]. In an aptitude test, administered to 900 college students, the mean was found to be 50
and S.D. to be 20. Find-

(a) The number of students securing between 30 and 70

59 Prof. Balaram Pd. Sharma

(b) Find the value of the score exceeded by the top 90 students.

Given:

Area 0.3413 0.3997 0.4015 0.4332

Z value 1.00 1.28 1.29 1.50
[Solve it]

[13]. In an examination the average marks secured by 400 students is 45 and S.D. is 10.
Assuming the distribution to be normal, Find-

(a) The number of students securing marks between 50 and 60

(b) The range of marks within which middle 50% of students would lie. [Solve it]

[14]. A normal distribution has SD=10. Find its mean if the probability that the random variable
takes on a value less than 80.5 is 0.3264. [Solve it]

[15]. A normal distribution has mean= 77. Find its standard deviation if 20% of the area under
the curve lies to the right of 90. [Solve it]

[16]. The entrance score of students in B.Sc. Forestry entrance examination is normally
distributed with mean score 65 and S.D. 10. Find,

(a) the lowest score of top 20% students

(b) the highest score of the lowest 30%

(c) the limits of scores within which the middle 50% of the students lie.

[Solve it]

60 Prof. Balaram Pd. Sharma