Random Variable

 For a given sample space S of some experiment, a random variable (rv) is any
rule that associates a number with each outcome in S.
 In mathematical language, a random variable is a function whose domain is
the sample space and whose range is the set of real numbers.
 Random variables are customarily denoted by uppercase letters, such as X
and Y .
 The notation X(s) = x means x is the value associated with outcome s by the
random variable X.
Types of Random Variables

Discrete Continuous
 It is a random variable whose  A random variable is continuous if
possible values either constitute a both of the following apply:
finite set or else can be listed in an
1.Its set of possible values consist
infinite sequence in which there is
either of all the numbers in a single
a first element, a second element
interval on the number line or a
and so on.(“countably” infinite)
disjoint union of such intervals (eg.
[10,20] U [20,30] )
2. No possible value of the variable
has a positive probability, that is,
P(X=c) = 0 for all c.
Probability distributions

 The probability distribution describes how the outcomes of an experiment are

expected to vary.
 Every random variable has a probability distribution associated with it.
 2 types of probability distributions:
1. Discrete: Binomial , Hypergeometric , Poisson
2. Continuous: Normal , Exponential
Binomial distribution

Properties of binomial distribution:

1. The experiment consists of n trials.
2. Each trial results in either a Success or a Failure.
3. The trials are independent of each other. The outcome of any one particular
trial does not influence the outcome of any other trial.
4. The probability of success P(S) is constant from trial to trial; we denote this
probability by p.
Examples

Experiment 1 : A coin is tossed n times and getting heads is considered a

success.

Satisfies all the properties of a binomial distribution.

Binomial random variable

 The binomial random variable X associated with a binomial experiment

consisting of n trials is defined as

X = the number of S’s(successes) among the n trials

Example : Tossing a coin 3 times.
S = success = Getting a heads
Here n=3
Sample Space= { HHH, HHT , HTH, HTT, THH, TTH, THT ,TTT}
Random variable X corresponding to each sample point can be found out as:
 X(HHH) = 3
 X(HHT) =2
 X(HTH) = 2
 X(HTT) = 1
 X(TTT) = 0
 X(THH) = 2
 X(THT) = 1
 X(TTH) = 1
 Hence, possible values of X in a 3 trial experiment here are x = 0,1,2,3
 In an n-trial experiment random variable X takes the values x = 0,1,2….,n.
 X ̴ B(n,p) , It implies that X is a binomial random variable with n
trials and success probability as p.

 Probability distribution of X will be:

b(x; n,p) = (n-x)
when x=0,1,2…..,n
0 otherwise
Example

 Question : What is the probability of getting 2 tails when a coin is tossed 4

times?
Solution

 Let’s make the probability distribution for this experiment:

X = The number of successes i.e. # tails
Outcome x Probability Outcome x Probability
HHHH 0 (1-p)4 TTTT 4 p4
HHTT 2 p2(1-p)2 TTHH 2 p2(1-p)2
HHTH 1 p(1-p)3 TTHT 3 p3(1-p)
HHHT 1 p(1-p)3 TTTH 3 p3(1-p)
HTTT 3 p3(1-p) THHH 1 p(1-p)3
HTHH 1 p(1-p)3 THTT 3 p3(1-p)
HTHT 2 p2(1-p)2 THTH 2 p2(1-p)2
HTTH 2 p2(1-p)2 THHT 2 p2(1-p)2
Solution

b(2; 4, p) = p2(1-p)2 + p2(1-p)2 + p2(1-p)2 + p2(1-p)2 + p2(1-p)2 + p2(1-p)2

= 6 p2(1-p)2

Hence , b(2; 4, p) = { no. of outcomes . { probability of any particular

with x=2} outcome with x= 2}
Question

 Ques.1. A dice is rolled 5 times. Success is defined as getting a 6 in a trial.

Find the probability of getting a 6 in (a) 2 rolls of the dice
(b) atleast 4 rolls of the dice
(c) atmost 4 rolls of the dice
Characteristics of Binomial Distribution

1. Shape
a) It may be symmetric or skewed.
If p = 0.5 the distribution is symmetric irrespective of value of n.
If p > 0.5 the distribution is negatively skewed.
If p < 0.5 the distribution is positively skewed.
For a given value of p , the distribution tends to symmetry as n increases
irrespective of the difference between p and q.
 Characteristics of Binomial Distribution

2. Parameters

A binomial distribution may be defined completely by the number of trials n, and

the probability of success in each trial p.
i.e. X ̴ B(n,p)
Characteristics of Binomial Distribution

3. Constants

Expected value of Binomial random variable

E(X) = np

Variance of Binomial random variable

σ2 = npq
Question

 Ques 1. Find the binomial distribution whose , mean =3 and variance = 2.

Hypergeometric distribution

 The hypergeometric distribution deals with situations in which samples are

selected without replacement from a finite population.
 Similar to binomial distribution, with the significant difference that the trials
are not independent.
Illustration
 Let N be the entire population .
 N consists of two kinds of elements N1 and N2.
 Let n elements be randomly drawn without replacement from this
population .
 We want to find the probability that x elements are from N1 and (n-x) from
N2.
Probability distribution of
Hypergeometric
 h(x; N,N1,n) =
Expected value of Hypergeometric r.v.
E(X) =
Variance of Hypergeometric r.v.
σ2 = n..
Question

Ques 1. A set of 10 tubes contains 3 defective tubes. If a sample of 3 tubes is

taken randomly , what is the probability that it will consist of :
(a) 2 good tubes and 1 defective tube?
(b) All 3 good tubes?
Poisson Distribution

 In a Poisson process, we are concerned with a random variable X, called the

Poisson variable , in a process which is characterised by the expected number
of successes per unit of time or space.
 The Poisson probability distribution gives the probability of a certain number
of successes 0,1,2,3…etc when an average number of such occurrences in a
certain interval is λ.
 P(x) = e-λ
where e = 2.7183 (a mathematical constant)
λ = the expected number of successes
x = the number of successes
P(x) = the probability of x successes
Examples

 The number of calls received at the reception counter per minute during a
certain hour of the day
 The no. of accidents per day on a highway
 The no. of arrivals at an ATM in every 5 minute period
 The no. of defects per metre of wire
Imp points

1. The minimum no. of successes in a Poisson distribution is 0 while there is no

upper limit.
2. Value of λ should be carefully defined. For eg ; It is given that on average ,
12 accidents occur in a quarter of a year on a certain crossing. In
calculating probabilities,
(a) A certain no. of accidents to occur over a month, we should take λ= 4.
(b) A certain no. of accidents to occur over a two month period, we should take
λ= 8.
 (c) A certain no. of accidents to occur over a three month period , we should
take λ= 12.
(d) A certain no. of accidents to occur over a one-and-a-half month, we should
take λ= 6.
Question

 If, on average, 2 customers arrive at a shopping mall per minute, what is the
probability that
(a) In a given minute, exactly 3 customers will arrive?
(b) In a given minute, no customer will arrive?
(c) In a given minute, more than 2 customers will arrive?
(d) In a 5-minute period, exactly 10 customers will arrive?
Characteristics of Poisson distribution

1. Shape
It is positively skewed. The degree of skewness decreases with an increase in
the value of λ.

2. Parameter
Single parameter λ.
Each value of λ yields a particular Poisson distribution
Characteristics of Poisson distribution

3. Constants
Expected value of Poisson distribution:
E(X) = λ

Variance of Poisson distribution:

V(X) = λ
Continuous Random Variable

 A random variable X is continuous if:

1. Possible values comprise either a single interval on the number line or a
union of disjoint intervals
2. P(X=c) = 0 for any number c that is a possible value of X.
Probability Distribution of continuous r.v.

 Let X be a continuous r.v. The pdf of X is a function f(x) such that for any two
numbers a and b with a<=b,

P(a<=X<=b) =

The probability that X takes on a value in the interval [a,b] is the area above this
interval and under the graph of the density function.
The graph of f(x) is called the density curve.
 For f(x) to be legitimate pdf, it must satisfy the following two conditions:
1. f(x) >= 0 for all x

= area under the entire graph of f(x)

Normal Distribution

 A variable X has normal distribution if its curve is given by the following

equation:

f(x) =

e = 2.7183

= 3.1416
Properties of Normal Distribution

1. It is a unimodal , bell shaped and symmetrical curve. Its mean , median and
mode are all equal.
2. For every value of x, f(x) > 0.
The normal curve is asymptomatic to the x-axis so that it approaches the
horizontal axis on both the ends but never touches it.

3. A normal distribution is defined by two parameters, its mean,µ, and its

standard deviation,σ.
Corresponding to each pair of these , a distinct normal curve exists.
4. A normal curve has 2 points of inflection. They are situated at 1 σ distance
from mean on either side of it.

5. If x1, x2, x3,…….. Are independent variables and each one is normally
distributed , then their sum x1 + x2 + x3+ ….+xn = x is normally distributed .

6. A normal curve being symmetric about µ , means area under it to the left of µ
is equal to the area under it to the right of µ.
 Under normal curve:
µ +/- σ = 68.27
µ +/-2σ = 95.45
µ +/- 3σ = 99.73
Standard normal (Z)

 Z is normally distributed with mean = 0 and standard deviation = 1.

Z Score :
z=

We look for the standard normal probabilities using the standard normal table.
Question

 Ques.1 A machine fills coffee powder in pouches with an average of 200gm

and a standard deviation of 4gm. Assuming that the coffee weight is normally
distributed, find the probability that a coffee pouch selected at random will
contain the following quantity of coffee:
(a) Atleast 200gm
(b) Between 200gm and 206gm
(c) Between 195 and 205 gm
(d) Less than 196 gm