Mathematical Expectation

Historically, the term mathematical expectation pr expected value is derived from games of
chance. In such games, the gamblers were concerned with how much, on the average, one would
expect to win if the game is continued for a sufficiently long time. In statistical terminology, this
term is associated with a random variable and in fact, is the average value of this random
variable generated through a random experiment.

The computation of expected value of a random variable is straight forward. When the variable is
discrete, it is simply the sum of the products of all possible values of the random variables
multiplied by their respective probabilities. For continuous variable, it is analogously defined.

Definition:
If X is a discrete random variable with the probability function f(x), then the expected value or
the mathematical expectation of X, E(X), is defined as

E ( X )=∑ xf (x )
x

If X is continuous having a density function f(x), then

+∞
E ( X )=∫ xf ( x ) dx
−∞

Example #01:

Suppose a lot contains 4 items. Let the random variable X denotes the number of defective items
in the lot. Suppose the probability function of the random variable X is

X:x 0 1 2 3
P(x) .50 .3 .15 .05
Find the expected number of defective items in the lot.

E ( X )=∑ xf ( x )
x

¿ 0 ×.50+1 ×.3+ 2× .15+3 ×.05

¿ .75
Example#02:

A fair coin is tossed twice. Then the number of heads is a random variable that takes values 0,1,2
with the following probability function

X:x 0 1 2
P(x) .50 .3 .2
Find the expected number of heads.

E ( X )=∑ xf ( x )
x

¿ 0 ×.50+1 ×.3+ 2× .2

Example #03

In a coin tossing game, a man is promised to receive TK. 5 if he gets all heads or all tails when
coins are tossed three times and he plays off (loses) TK. 3 if either one or two heads appear. How
much is he expected to gain in the long run?

Let,

X= no. of heads in the toss

Outcome No. of heads P(x) Gain

HHH 3 1/8 5
HTT 1 1/8 -3
HHT 2 1/8 -3
THT 1 1/8 -3
THH 2 1/8 -3
TTH 1 1/8 -3
HTH 2 1/8 -3
TTT 0 1/8 5

E ( X )=∑ xf ( x )
x

2 6
¿ 5 × −3 ×
8 8

¿−1
Example #04

A life insurance company in Bangladesh offers to sell a TK. 25000 one year term life insurance
policy to a 25 years old man for a premium of TK. 2500. According to Bangladesh life table, the
probability of surviving one year for a 25 year old man is .97 and of dying is .03. What is the
company’s expected gain in the long run??

Let,

X= The gain which can take values TK. 2500, if the man survives, and (2500-25000)= -22500 if
the man dies

The probability distribution

x 2500 -22500
P(x) .97 .03

E ( X )=∑ xf ( x )
x

¿ 2500 ×.97−22500 ×.03

¿ 1750

Consider the following PDF

1
f ( x )= x 0< x < 4
8

¿ 0 , elsewhere

Find E(X)
+∞
E ( X )=∫ xf ( x ) dx
−∞

4
x
E ( X )=∫ x dx
0 8
Variance of a discrete random variable:
If X is a discrete random variable with mean μ which can take values x 1 , x 2 ,… … .. x n with the
associated probabilities p ( x 1 ) , p ( x 2 ) … … … . , p ( x n ) , then the variance of X denoted by σ 2 is
defined as

σ 2=E[ X −E ( X ) ] =E [ X−μ] 2=E [ X 2 ]−[E ( X ) ]

2 2

Here, E [ X 2 ]=x 21 p ( x1 ) + x 22 p ( x 2 ) +… … … .+ x2n p ( x n )

Example #05

Let the random variable X have the following probability distribution

x: -1 0 1
f(x): .2 .3 .5
Compute the expected value of

i. E(X)
ii. E(2X)
iii. E(X+2)
iv. E(X2)
v. E(3X+1)

Properties of expectation:

1. E(C)= C
2. E(CX)=CE(X)
3. E(a+bx)=a+bE(X)
4. V(C)= 0
5. V(a+bx)=b2V(X)
In this section we shall discuss some important probability distributions, which are found to have
wide applications in real life. There are a large number of probability distributions, but we shall
limit ourselves only in three important probability distributions, two of which are discrete and
the other is continuous. The two discrete distributions are

1. Binomial distribution and

2. Poisson distribution

Moreover, we shall discuss the most important continuous distribution known as normal
distribution.

Some concepts related to binomial distribution are discussed below.

Bernoulli trial:
Binomial distribution is related with Bernoulli trial. A trial is an unit experiment. An experiment
is called Bernoulli trial if it has two possible outcomes namely success and failure. For example,
in a die throwing experiment, if our desired number is six, then six is our success and other is our
failure. The probability of success as well as the probability of failure remains same from trial to
trial.

Binomial Experiment:
An experiment is a binomial experiment when it has the following properties:

1. The experiments consists of n Bernoulli trials.

2. Each trial has two possible outcomes namely success and failure.
3. The probability of success remains same from trial to trial.
4. The repeated trials are independent.

Binomial Distribution:
A discrete random variable X is said to have a binomial distribution if its probability function is
defined by

p ( x )=nC p x qn−x ; x=0 ,1 , 2… … .n

x

Where p+q=1

The binomial variable X with parameter n and p is symbolically written as X B(n , p).
The unknown constants required to define a distribution are called the parameters of the
distribution. A distribution is completely known if the parameters are known.

Mean and Variance of the distribution:

Mean E ( X )=μ=np

Variance σ 2=npq

SD σ =√ npq

Example:

Suppose X is a binomial variate with parameters n=4 and p=.45.Find the following probabilities

1. P[X=2]
2. P[X>3]
3. P[X≤ 2]

Example:

Warranty records show that the probability that a new car needs a warranty repair in the first 90
days is .05. If a sample of three new cars is selected, what are the probabilities that in the first 90
days

i. None needs a warranty repair?

ii. At least one need warranty repair?
iii. More than one needs a warranty repair?
iv. What is the mean and SD of the number of cars need warranty repair?

Some important properties of binomial distribution

1. It is a discrete probability distribution with parameters n and P.

2. The mean of the distribution is np and its variance is npq. Mean of the distribution is
greater than the variance.
3. The distribution is positively skewed if p<1/2 negatively skewed if p>1/2
4. The distribution is symmetric if p=q=1/2
5. The distribution tends to the Poisson distribution if the number of trials, n tends to
infinity.
6. The distribution tends to normal distribution if n tends to infinity and p or q is not so
small
7. P ( X=n )= pn and P ( X=0 )=q n
Poisson distribution:

Poisson distribution was discovered by the French mathematician a physicist Simon Denis
Poisson [1781-1840], who published it in 1837. It has many applications in modern day life such
as modeling the radioactive decay, predicting the number of telephone calls arriving at an
exchange, etc. Poisson distribution is a limiting case of the binomial distribution under the
following conditions:

1. The probability of success or failure in Bernoulli trial is very small. That is p →0∨q → 0
2. n, the number of trial is very large and
3. np= λ is a finite constant.

Definition:

A discrete random variable X is said to have a Poisson distribution if its probability function is
defined by
−λ x
e λ
p ( x )= ; x=0 ,1 , 2 ,… … ,∞
x!

where e=2.71828 and λ is the only parameter of the distribution which is the mean of the
distribution.

Poisson variable X with parameter λ is written as X P(λ)

Characteristics of Poisson distribution:

1. The number of successes occurring in one time interval is independent of those occurring
in other disjoint time interval
2. The probability of single success occurring during a very short time interval is
proportional to length of the time interval and does not depend on the number of success
occurring outside the interval.
3. The probability of more than one success in such a short time interval is negligible.

Some important properties of Poisson distribution:

1. The mean and variance of the distribution is λ

2. When λ tends to infinity, Poisson distribution tends to normal distribution.
3. The distribution is positively skewed and leptokurtic.

Some practical applications of Poisson distribution

1. The number of car passing through a certain street in time t

2. The number of suicides reported per day of a certain area