PROBABILITY DISTRIBUTIONS

Review of basic probability theory:

1. Probability: A probability is a number that reflects the chance or likelihood that a
particular event will occur.
2. Probabilities can be expressed as proportions that range from 0 to 1.
3. Probabilities can also be expressed as percentages ranging from 0% to 100%.
4. A probability of 0 indicates that there is no chance that a particular event will occur,
whereas a probability of 1 indicates that an event is certain to occur.

Examples:

 Tossing a coin.
 Throwing a die.
 Random drawing of cards from a pack of cards and so on.
 The theory of probability concept has been given an exact mathematical significance for
being used widely in the areas of study as
Mathematics

Statistics
Finance

Science and philosophy

Gambling so on.

5. GENERAL RULE OF PROBABILITY: If an event happens m times and it fails and n

times, then the probability of the event A is defined as
m
P(A) 
mn

(OR)

Number of cases favorable to the occurrence of the event

P(A) 
Total number of mutually exclusive and exhaustive cases

6. Probability in favor of the occurrence of the event:

m Number of cases favorable to the occurrence of the event

n The number of cases against the occurrence of the event
7. Probability against the occurrence of the event:
 n The number of cases against to the occurrence of the event

m The number of cases favorable to the occurrence of the event
8. Experiment: An experiment is a process that generates well-defined outcomes. On any
single repetition of an experiment, one and only one of the possible experimental outcomes
will occur.

Examples of experiments and their associated outcomes

Experiment Experiment outcomes

Toss a coin Head, tail

Select a part for inspection Defective, non-defective

Conduct a sales call Purchase, no purchase

Roll a die 1, 2, 3, 4, 5, 6

Play a football game Win, lose, tie

9) Random Variables: A variable whose value is determined by the outcome of a random

experiment is called a random variable or stochastic variable or variate. It is denoted by capital
letter X, Y, Z,
Types of random variables: There are two types of random variable, namely,

a) Discrete random variable

b) Continuous random variable
10) Discrete and Continuous random variable: If a random variable takes a finite set of values,
it is called a discrete random variable. On the other hand, if it assumes an infinite number of
uncountable values, it is called a continuous random variable.

Example for discrete random variable:

 Tossing a coin and observing the outcome.

 Throwing a die and observing the numbers on the face.

Example for continuous random variable:

 Weight of articles.
 Height of individuals.

DISCRETE PROBABILITY DISTRIBUTION

 Suppose a discrete random variable X is the outcome of some experiment. If the
probability that X takes the values xi is pi, then

P (X= xi) = pi (or) p(xi) for i=1, 2, …

Where
i. p(xi) ≥ 0, for all i
 ii.  px   1
i

then p(x) is called a probability function.

 The set of values [xi, p(xi)] is called a discrete probability distribution of the random
variable X.
 P(X) is the probability density function (p. d. f) or probability mass function (p. m. f).
 MEAN, VARIENCE and STANDARD DEVIATION:
Mean (  )   x p ( x )
i i
i
2
Variance ( 2 ) or V    x    p ( x )   x 2 p( x )   2
i 
i i i i
i
Standard variance ( )  V

CONTINUOUS PROBABILITY DISTRIBUTION



 If f  x   0 and  f ( x) dx  1 then f(x) is called a continuous probability function (or)



probability density function.

 MEAN, VARIENCE and STANDARD DEVIATION:

Mean (  )   x f ( x) dx


Variance ( ) or V   x   
2 2
f ( x) dx


Standard variance ( )  V

PROBLEMS
1) The p. d. f of a variate X is given by the following table:

x 0 1 2 3 4 5 6
p(x) K 3k 5k 7k 9k 11k 13k
For what value of k, this represents a valid probability distribution. Also find p (x ≥ 5) and p (3 <
x ≤ 6).

Solution: The probability distribution is valid if p(x) ≥ 0 and  px   1.

Hence, we must have k ≥ 0 and

K + 3k + 5k + 7k + 9k + 11k + 13k = 1

1
k
49
49k=1

24
P (x ≥ 5) = p (5) + p (6) = 11k + 13k = 24k  and
49

33
p (3 < x ≤ 6) = p (4) + p (5) + p (6) = 33k  .
49

2) A random variable X has the following probability function:

x 0 1 2 3 4 5 6 7
2 2 2
p(x) 0 K 2k 2k 3k k 2 k 7k + k
i) Find the value of k, ii) Evaluate p (x < 6) and p (x ≥ 6) iii) p (0 < x <5).

Solution:
i) If X is a random variable, then
7

 p( x )  1
i 0
i

1
i.e., 0 + k + 2k +2k + 3k + k2 + 2 k2 + 7k2 + k = 1  k 
10

81
ii) p (x < 6) = p(x=0) + p(x=1) +…+ p(x=5) = 8k + k2 =
100

19
p (x ≥ 6) = p(x=6) + p(x=7) = 9 k2 + k =
100

4
iii) p (0 < x <5) = p(x=1) + p(x=2) + p(x=3) + p(x=4) = 8k =
5
3) A random variable X has the following probability function

x -2 -1 0 1 2 3
p(x) 0.1 k 0.2 2k 0.3 k
Find k and calculate mean and variance.

Solution: If X is a random variable then

 p( x )  1  k  0.1
i

Now the probability distribution is given by

x -2 -1 0 1 2 3
p(x) 0.1 0.1 0.2 0.2 0.3 0.1
 Mean (  )   x p ( x )  0.2  0.1  0  0.2  0.6  0.3  0.8
i i
i
Variance ( 2 ) or V   x 2 p ( x )   2  2.16
i i
i

TYPES OF PROBABILITY DISTRIBUTION:

In discrete probability distribution:
a) Binomial distribution
b) Poisson distribution

In continuous probability distribution

a) Exponential probability distribution

b) Normal probability distribution

BINOMIAL DISTRIBUTION (or) BERNOULLI DISTRIBUTION

If the probability of a successful trial is p and that of failure in any trial is q, then the probability
of having x successful outcomes in an experiment of n independent trials is as follows:

P ( X  x )  nC x p x q n  x

where

n = the number of trials

x = 0, 1, 2...n

p = the probability of success in a single trial

q = the probability of failure in a single trial (i.e. q = 1 − p)

p+q=1
P(x) gives the probability of successes in n binomial trials.
The following probability distribution of [x, P(x)]

x 0 1 2 … n
P(x) qn n
C1 p1 q n1 n
C 2 p 2 q n2 … pn

It may be observed that the value of P(x) for different values

x = 0, 1, 2, …, n are the successive terms in the binomial expansion of (q + p) n and this distribution
is called the binomial distribution.

 P( x )  q n
 n C1 p 1 q n 1  ...  p n  (q  p) n  1
Hence P(x) is a probability function.

 MEAN, VARIENCE and STANDARD DEVIATION OF THE BINOMIAL

DISTRIBUTION:
n
Mean (  )   x P( x)  np
x 0
n
Variance ( 2 ) or V   x 2 P( x)   2  npq
x 0

Standard variance ( )  V  npq

PROBLEMS
1) A coin is tossed 5 times. What is the probability of obtaining four or more heads.
Solution: When a coin is tossed the probability of head and tail in case of an unbiased coin are
equal i.e., p = q = 0.5. Here n =5

P( X  x)  nC x p x q n x
Formula:

5 1 6 3
The probability of obtaining 4 or more heads = P (4) + P (5) =   
32 32 32 16
2) The probability that a pen manufactured by a company will be defective is 0.1. If 12 such pens
are manufactured find the probability that

i) Exactly two will be defective

ii) At least two will be defective
iii) None will be defective
Solution: The probability of a defective pen, p = 0.1.
Therefore, the probability of non-defective pen, q = 1-0.1 = 0.9.
n x
Formula: P( X  x)  C x p q
n x
, where n = 12.

i) Probability of exactly two will be defective is

P(x=2) = 0.2301
ii) Probability of at least two will be defective
= 1- [p(x=0) + p(x=1)] = 0.3409
iii) Probability of none will be defective is p (x=0) = 0.2824.

1) In 256 sets of 12 tosses of a coin, in how many cases one can expect 8 heads and 4 tails.

Solution: P(head)=0.5=p: P(tail)=0.5=q

n x
Formula: P( X  x)  C x p q , where n = 12, x = 8
n x

The probability of 8 heads and 4 tails is

 495
P (X = 8) =
4096

 495 
The expected number of such cases in 256 sets = 256   =30.9 ≈ 31
 4096 

2) The bolts produced by a certain machine were checked by examining samples of 12. The
following table shows the distribution of 130 samples according to the number of defective items
they contained:

No. of defective in 0 1 2 3 4 5 6 7 Total

sample of 12
No. of samples 7 6 19 35 30 23 8 2 130
Fit a binomial distribution and find the expected frequencies if the chance of bolt being defective
is ½. Find the mean and variance of the fitted distribution.

Solution:

No. of defective f ( x)  nC x p x q n x Expected frequency = N

x f(x)
0 1 1
0
1
7 1.01
F (0)  C0     
7

2 2 128

1 1 1
1
7
6 7.11
F (1)  C1     
7

2 2 128

2 1 1
2
21
5 21.33
F (2)  C2     
7

 2   2  128
3 1
3
1
4
35 35.55
F (3)  7C3     
2 2 128
4 1 1
4
35
3 35.55
F (4)  7C4     
 2   2  128
5 1 1
5
21
2 21.33
F (5)  C5     
7

2 2 128

6 6
1 1
1
7 7.11
F ( 6)  C 6     
7

 2   2  128
7 1 1
7
1
0 1.01
F (7 )  C 7     
7

 2   2  128
Mean= np=7 (1/2) =3.5

Variance=n p q=7(1/2) (1/2) =1.75

3) The mean and variance of a binomial variable X are 4 and 2 separately. Find the probability that
X takes values greater than 3.

Solution:
Mean = np = 4 ----(1)
Variance = n p q = 2-- (2)
(2) / (1), then q = ½, p = 1-q = 1-1/2=1/2.

Put p value in (1), we get n =8.

Now,

P (X > 3) = P (X = 4) + P (X = 5) + P (X = 6) + P (X = 7) + P (X = 8)
=163 / 256
= 0.636

POISSON DISTRIBUTION
Poisson distribution (P. D.) arises when count a number of events across time or over an area.

Poisson distribution is a discrete random variable distribution that expresses probability of the
given number of events in a fixed interval of time, if these events occur with a known average rate
and independent of the time since the last event.

Poisson distribution is regarded as the limiting form of the binomial distribution when n is very
large (n →∞) and p the probability of success is very small (p →0) so that np tends to a fixed finite
constant say m. The poisson distribution of the random variable is

e m  m x
PX  x  
x!

x: 0 1 2 3 … Total

-m
P(x) em  m em  m2 e  m  m3 … 1
e
2! 3! (as the total probability must be unity)

 MEAN, VARIENCE and STANDARD DEVIATION OF THE POISSON

DISTRIBUTION:
Mean = m
Variance = m
S.D = (m)1/2

PROBLEMS
1) If 4% of the electric geysers manufactured by a company are defective, use poisson distribution
to find the probability in a sample of 100 geysers when:
i) None is defective ii) 5 geysers are defective (Given: e -4 = 0.018).

Solution: Let p = probability of a defective geyser = 4% = 0.04.

Given, n = 100, p = 0.04;
Mean = np = 100(0.04) =

m
The Poisson distribution is given as: P X  x   e  m
x

x!

i) None are defective

e 4  4 0
P X  0    e 4  0.018  P(0)
0!

ii) 5 geysers are defective:

e 4  45
P  X  5   0.154  P(5)
5!

2) 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
approximation number of packets containing no defective, one defective and two defective
blades respectively in a consignment of 10,000 packets.
Solution: We know that m = np = 10 (0.002) = 0.02; e-0.02 = 0.9802

e m  m x
The Poisson distribution is given as: P X  x  
x!

P (no defective blade) = P(x=0) = 0.9802

Therefore, number of packets containing no defective blade is

10,000 (0.9802) = 9802

P (one defective blade) = P(x=1) = 0.019604

Therefore, number of packets containing no defective blade is

10,000 (0.019604) = 196

P (two defective blades) = P(x=2) = 0.00019604

Therefore, number of packets containing no defective blade is

10,000 (0.00019604) ≈ 2
3) The following table gives the number of days in a 60 day period during which road accidents
occurred in a town. Fit Poisson distribution to the data:

No. of accidents 0 1 2 3 4
No. of days 31 18 7 3 1
Find the expected frequencies.

Solution:

Fitting of Poisson Distribution

X f fx
0 31 0
1 18 18
2 7 14
3 3 9
4 1 4
∑ 𝑓=N=60
∑ 𝑓 𝑥 = 45

∑𝑓 𝑥 45
Mean = ∑𝑓
= 60 = 0.75 = m

f 0   e m  0.4724; f 1  m f (0)  0.75 (0.4724)  0.3543; f (2) 

m
f (1)  0.1329;
2
m m
f (3)  f (2)  0.0332; f (4)  f (3)  0.0062
3 4

In order to fit Poisson distribution, we shall multiply each probability by N, i. e., 60.

Hence, the expected frequencies are:

x f
0 0.4724 x 60 = 28.34
1 0.3543 x 60 = 21.26
2 0.1329 x 60 = 7.97
3 0.0332 x 60 = 1.99
4 0.0062 x 60 = 0.372

EXPONENTIAL DISTRIBUTION
The continuous probability distribution having the probability density function f(x) is given by
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
𝑓 (𝑥 ) = { is known as the exponential distribution.
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒, 𝑤ℎ𝑒𝑟𝑒 𝛼 > 0

 MEAN, VARIENCE and STANDARD DEVIATION OF THE EXPONENTIAL

DISTRIBUTION:
 
1
Mean (  )   x f ( x) dx  


1
Variance ( 2 ) or V   ( x   ) 2 f ( x) dx  2


1
Standard variance ( ) 


𝑘 𝑥 2, 0 < 𝑥 < 3
1) Find the constant k such that 𝑓 (𝑥 ) = { is a p.d.f. Also compute
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
i) P (1< x < 2) ii) P (x ≤ 1) iii) P (x ≥ 1) iv) Mean v)
Variance

Solution: f x  0 if k  0 .

Also, we must have  f ( x) dx  1


3
3
x3  1
i.e.,  k x 2 dx  1  k   1 (or) k 
0 3 9
0

2
x3 
2 2 2
x 7
i) P(1 < x < 2) =  f ( x) dx   dx  
27  27
1 1
9
 1
1
x3 
1 1
x2 1
ii) P(x  1) =  f ( x) dx   dx  
27  27
0 0
9
 0
3
x 3  26
3 3
x2
iii) P(x  1) =  f ( x) dx   dx  
27  27
1 1
9

1
3
x 4  81 9
 3
x2
iv) Mean =  x f ( x) dx   x dx   
36  36 4
 0
9
 0
 2
9
3
x2
Variance =  x 2 f ( x) dx      x 2
81 81 27
dx      
2
v)
 0
9 4 15 16 80

2) A random variable x has the following density function

𝑘 𝑥 2, − 3 ≤ 𝑥 ≤ 3
𝑓 (𝑥 ) = { evaluate k and find
0, 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
i) P (1≤ x ≤ 2) ii) P (x ≤ 2) iii) P (x ≥ 1)
Solution: f x  0 if k  0 .

Also, we must have  f ( x) dx  1


3
x3 
3
1
i.e.,  k x dx  1  k
2
 1 (or) k 
3 3 
 3 18

2
x2 x3 
2
7
i) P(1  x  2)  dx 
54 

1
18 1 54
2
x2 x3 
2
35
ii) P( x  2)  dx 
54 

3
18 3 54
3
x2 x 3  26
3
iii) P( x  1)  dx 
54 

1
18 1 54

1) The kilometer run (in thousands of Kms) without any sort of problem in respect of a certain
−𝑥
1
vehicle is a random variable having p. d. f. 𝑓 (𝑥 ) = {40 𝑒 , 𝑥 ≥ 0 Find the probability that the
40

0, 𝑥 ≤ 0
vehicle is trouble free

i) At least for 25000 Kms

ii) At most for 25000 Kms
iii) Between 16000 to 32000 Kms
Solution: x is the random variable representing Kms in multiples of 1000 regarding trouble free
run by the vehicle.

i) P( x  25)  1 - P(x  25)  1 -

25


1 40
40
x
x
e dx  1  e 40  25

0
5
 1  e 8  1  0.5353


0
25 x 25 5
1 40 x
ii) P( x  25)   40
e dx   e 40
0
 e 8  1  0.4647


0
32 x 32 4 2
1 40 x
iii) P( 16  x  32)  
16
40
e dx   e 40
16
 e 5  e 5  0.221

2) If x is an exponential variate with mean 3 find i) P(x > 1) ii) P(x < 3).

Solution:
𝛼 𝑒 −𝛼𝑥 𝑓𝑜𝑟 𝑥 > 0
Formula: 𝑓(𝑥 ) = {
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒, 𝑤ℎ𝑒𝑟𝑒 𝛼 > 0
1 1
Mean =  3;  .
 3
 i) P (x > 1) =0.7165
ii) P (x < 3) =0.6321

NORMAL DISTRIBUTION
The continuous probability distribution having the p. d. f. f(x) given by
( x )2
1
f ( x)  e 2 2
,    x  ,       and   0
 2

is known as the normal distribution.

 MEAN, VARIENCE and STANDARD DEVIATION OF THE NORMAL

DISTRIBUTION:

Mean (  )   x f ( x) dx  


Variance ( 2 ) or V   ( x   ) 2 f ( x) dx   2


Standard variance ( )  

NOTE: The graph of the probability function f(x) is a bell-shaped curve symmetrical about the
line x=  and is called the normal probability curve. The shape of the curve is as follows:

f(x)

x
x=μ

Properties of a normal distribution

 The mean, mode and median are all equal.

 The curve is symmetric at the center (i.e. around the mean, μ).
 Exactly half of the values are to the left of center and exactly half the values are to the
right.
  The total area under the curve is 1.

STANDARD NORMAL DISTRIBUTION

x
1. z  is called the standard normal variate (SNV).

z2
1 
2. F ( z )  e 2
is the Standard normal probability density function or standard
2
normal curve.
z z2
1 
3.  ( z ) 
2
e
0
2
dz represents the area under the standard normal curve from 0 to z.

SOME IMPORTANT RESULTS


(i ) P   z       ( z ) dz  1

0
(ii ) P   z  0     ( z ) dz  0.5


(iii ) P0  z       ( z ) dz  0.5
0

(iv ) P z  z1   0.5   ( z1 )
(v) P z  z 2   0.5   ( z 2 )

PROBLEMS
1) In a normal distribution 31% of the items are under 45 and 8% of the items are over 64. Find
the mean and S. D. of the distribution.
Solution: Let μ and σ be the mean and S. D. of the normal distribution.
Given, P (x < 45) = 0.31 and P (z > 64) =0.08.

x
We have, SNV: z 

45  
When x = 45, z   z1 ( say ) -------- (1)

64  
x = 64, z   z 2 ( say ) --------(2)

Thus, we have,
P z  z1   0.5   ( z1 )  0.31 and Pz  z 2   0.5   ( z 2 )  0.08

 ( z1 )  0.19;  ( z 2 )  0.42
From table : 0.1915  0.19   (0.5) and 0.4192  0.42   (1.4)
 ( z1 )   (0.5) and  ( z 2 )   (1.4)
z1  0.5 and z 2  1.4

Substitute in (1) and (2), we get

  0.5  45 and   1.4  64
By Solving, we get   50 and   10

2) In an examination 7% of students score less than 35 marks and 89% of students score less
than 60 marks. Find the mean and standard deviation if the marks are normally distributed. It is
z z2
1 
given if  ( z ) 
2
e
0
2
dz

Then  (1.2263)  0.39 and  (1.4757)  0.43

Solution: Let μ and σ be the mean and S. D. of the normal distribution.

Given, P (x < 35) = 0.07 and P (z < 60) =0.89.

x
We have, SNV: z 

35  
When x = 35, z   z1 ( say ) -------- (1)

60  
x = 60, z   z 2 ( say ) --------(2)

Thus, we have,

Pz  z1   0.5   ( z1 )  0.07 and Pz  z 2   0.5   ( z 2 )  0.89

 ( z1 )  0.43;  ( z 2 )  0.39
 ( z1 )   (1.4757) and  ( z 2 )   (1.2263)
z1  1.4757 and z 2  1.2263

Substitute in (1) and (2), we get

  1.4757  35 and   1.2263  60
By Solving, we get   48.65 and   9.25

3) The life of an electric bulk is normally distributed with average life of 2000 hours and S. D. of
60 hours. Out of 2500 bulbs. Find the number of bulbs that are likely to last between 1900 and
2100 hours. Given that P (0 < z < 1.67) = 0.4525.
Solution: Given, μ=2000 and σ=60.
 x
We have, SNV: z 

To find P (1900 < x < 2100)
If x = 1900, then z = -1.67,

If x = 2100, then z = 1.67

P (1900 < x < 2100) = P (-1. 67 < z < 1.67) = 2 P (0 < z < 1.67) =2(0.4525) =0.905

Number of bulbs that are likely to last between 1900 and 2100 hours
=2500 (0.905) = 2263.