Random Variable

A real valued function defined over sample space of a random experiment is called random variable
associated to that random experiment. That is, random variable is a variable which takes values depending
on the outcome of a random experiment.

Eg: Consider the random experiment of tossing two coins together. Here the sample space is S={(H,H),
(H,T),(T,H),(T,T)}. Let us define a variable X by the no. of heads obtained. Then X takes the values 0, 1
and 2 depending on the outcome of the experiment. Here X is a random variable.

Discrete and Continuous random variable

A random variable X is said to be discrete if it can take either a finite no. of values or countable infinite
no. of values.

A random variable which is not discrete is called continuous. A continuous random variable can take all
possible values between two numbers.

Eg: Height of a student selected at random from a college.

Probability distribution of a random variable

Discrete

Let X be a random variable which takes values x 1,x2,x3,……Let x stand for anyone of x1,x2,x3,……Then
probability that the random variable X takes the value x defines as probability distribution of X and is
denoted by P(x) = P(X=x).

Properties of Probability Distribution

Let P(x) be the probability distribution of a random variable X. Then,

(1) P(x) ≥ 0 for all values of x

(2) ∑P(x) = 1

Continuous

If X is a continuous random variable and if P (x≤ X ≤ x+dx) =f(x)dx, then f(x) is called probability
density function (pdf) of X, provided it satisfies the following conditions.

(i) f(x) ≥ 0 for all values of x

(ii) ∫ f(x)dx = 1

Expected value of a random variable

Let X be a discrete random variable assuming the values x 1,x2,x3,……xn with respective probabilities
p1,p2,p3,……pn then the expected value or mean value of X is defined as

E(X) = x1p1 + x2p2 + ……+ xnpn

= ∑ xipi where ∑ pi = 1

If X is a discrete random variable with f(x) as its probability mass function (pmf) then E(X) = ∑xf(x)

If X is a continuous random variable defined in the interval -∞ to ∞ having f(x) as it pdf then E(X) =
∫xf(x)dx
 Theoretical Probability Distribution

When values of a random variable are distributed according to some law, which can be expressed
mathematically, such distributions are known as theoretical distributions. Binomial distribution, Poisson
distribution, normal distribution and exponential distribution are t6he important distributions. The first
two are discrete probability distributions and the last two are continuous probability distributions.

Binomial Distribution

A trial which when performed results either in the occurrence of an event called success or in its non-
occurrence called failure is called a Bernoullian trial. Further in a Bernoullian trial the probability for
success (denoted by p) and the probability for failure (denoted by q) remain the same for all trials so that
p+q = 1.

Consider n independent Bernoullian trials. Let x be the number of success obtained. Then there are n-x
failures. One way of getting x successes and n-x failures is

SSS…..S FFF…..F

Probability for this is ppp….p qqq….q

The probability of any sequence of results in which there are x successes and n-x failures is p xqn-x. x
successes can occur in n trails in nCx different ways.

Hence probability of getting x successes and n-x failures in n trails is nCx p xqn-x

Definition
A random variable X is said to follow Binomial distribution if the pmf of X is given by

P(X=x) = nCx pxqn-x

where x = 0,1,2,…..,n
0 ≤p ≤1
p+q = 1

Mean = np
Variance = npq

When X follows Binomial distribution with parameters n and p, we write X ~ B (n,p)

Poisson Distribution

Poisson distribution is the limiting form of Binomial distribution under certain very general conditions.

1) The number of independent trials is indefinitely large i.e, n →∞

2) The probability for success in a single trial is indefinitely small i.e, p→ 0
3) np = λ, a finite quantity

Under the above three conditions, the Binomial distribution assumes another convenient from klnow2n as
Poisson distribution.
The statement that p is very small implies that the probability for occurrence of event is very small.
Events having very small probability for occurrence are termed as rare events. Hence Poisson distribution
is always associated with occurrence of rare events. The following are some examples where Poisson
distribution can be conveniently applied.

1) No. of deaths due to snake bite

2) No. of defective items in a lot supplied by a good manufacturing concern
3) No. of printing mistakes on a page typed by a good typist
4) No. of traffic accidents in a particular city per week
5) No. of accidents in a particular city.

The pmf of Poisson distribution is given by P(X=x) = e - λ λx/x! where x = 0,1,2,…..,∞ and λ is called the
parameter of the Poisson distribution. In this case we can write X ~ P(λ)

Mean = λ = Variance

Uses of Poisson Distribution

The Poisson Distribution can be practically applied to several operations that are common for companies.

1. To count the number of telephone calls arriving at a telephone counter in unit time
2. To count the number of customers arriving at a super market , say per hour
3. To count the number of defects per units of a manufactured product
4. To count the number of accidents taking place in a day on a busy road

Normal Distribution

X is a continuous random variable defined in the interval (-∞,∞). It is said to follow normal distribution,
if its probability density function is given by (Look at notes given in the class).

Standard normal distribution

If X follows a normal distribution with mean 0 and SD 1, the X is said to follow standard normal
distribution. (Refer to notes given in the class for pdf)

The graph of normal distribution is bell shaped, symmetric at its mean. (Refer to notes given in the class
for graph).

Properties of Normal Distribution

1. The normal curve is a continuous curve

2. The normal curve is bell shaped
3. Normal curve is symmetric about the mean
4. No portion of the curve lies below the x-axis
5. The two tails of the normal probability distribution extend indefinitely and never touch the
horizontal axis
6. The height of the normal curve is maximum at its mean.
7. Mean, median and mode are equal for normal distribution
 8. If X and Y are two independent normal variates, then their sum X+Y is also a normal variate.
This is called the additive property.

Uses of normal distribution

1. As n becomes large, the normal distribution serves as a good approximation for many discrete
distributions (such as Binomial, Poisson, etc.).
2. Even if a variable is not normally distributed, it can sometimes be brought to normal form by
simple transformation of variable
3. The sampling theory and tests of significance are based upon the assumption that samples have
been drawn from a normal population with mean and variance
4. Normal distribution finds large applications in Statistical Quality Control.

The normal distribution has applications in many areas of business administration. For example,

1. Modern portfolio theory commonly assumes that the returns of a diversified asset portfolio follow
a normal distribution
2. In operation management, process variations often are normally distributed
3. In human resource management, employee performance sometimes is considered to be normally
distributed

Exponential Distribution

X is a continuous random variable defined in the interval (0,∞). It is said to follow normal distribution, if
its probability density function (pdf) is given by

f(x) = λ e- λx

where λ > 0 and x >0

Mean = 1/ λ and Variance = 1/ λ2