CSD4101 Probability and Statistics

Discrete and Continuous probability distributions

Discrete Probability Distribution

Discrete random variable

Let X be a r.v defined on sample space Ω.If the number of possible values of X is finite or countably
infinite then X is called a discrete r.v.

Ex. An unbiased die is tossed.

Probability distribution of a discrete random variable.

Let X be a discrete r.v. defined on sample space Ω. Let the range set of X consist of real values
x1,x2,…xn.To each real value xi, a number pi is assigned such that

i. pi ≥ 0 and ii. ∑pi = 1 , where pi = P(X = xi ).

The function P defined above is called probability mass function

( p.m.f ) . The set of ordered pairs ( xi , pi ) i= 1,2,…n is called univariate discrete probability
distribution of X or probability distribution of X.

Expected value or Mean of X

Let (xi,pi) i= 1,2,3,…n denote the probability distribution of a discrete r.v. X .

The matμhematical expectation or expected value of X is defined as

E(X) = ∑xipi

= x1p1 + x2p2 + … + xnpn

E(X) is also called as average value or mean of X

Variance of X

Let X be a discrete r.v. with probability distribution (xi,pi) i= 1,2,…n

Let the mean or E(X) of the probability distribution be denoted by μ. The variance of X denoted by σ2
is given by

Var(X) = E(X- μ)2 = ∑(xi – μ)2pi

= E(X2) – [E(X)]2

Note: V(X) ≥ 0 → E(X2) ≥ [E(X)]2

Distribution function of a discrete random variable

Let the probability distribution of a discrete r.v be

X : x1 x2 …. Xn

P(X=x): p1 p2 pn
For each value of X we calculate P(X≤ x) and represent it in the following table:

X : x1 x2 x3 …. xn

P(X≤ x): p1 p1+p2 p1+p2+p3 ∑pi = 1

The above table is known as cumulative distribution of r.v. X and the function

F(x) = P(X≤ x) is called distribution function of X. It is denoted by d.f

Ex. X : 0 1 2 3

P(X=x): 1/10 4/10 3/10 2/10

F(x) : 1/10 5/10 8/10 1

Important properties of distribution function

Let P(x) and F(x) denote the p.m.f and d.f of a r.v X respectively. F(x) has the following properties:

i. It is defined for every real value of X

ii. 0 ≤ F(x) ≤ 1

iii. It is a non decreasing function of X i.e if x1 ≤ x2 then F(x1) ≤ F(x2)

iv. It has jumps at each value of X

v. It has jumps between two successive values of X. It is also called as a step function.

vi. F(−∞ ) = 0 and F( ∞ ) = 1

Median and Mode of X.

Median is value of X for which F(x)≥ 0.5 for the first time.

Mode is value of X corresponding to maximum probability.

Ex.1. Verify whether the following can be regarded as a p.m.f for the given values of x

i. P(x) = (x+1)/10 x = 0,1,2,3

ii. P(x) = x2/30 x = 0,1,2,3,4

Iii P(x) = (x-2)/5 x = 1,2,3,4,5

Solution:

i. X: 0 1 2 3

P(x) : 1/10 2/10 3/10 4/10 p.m.f

ii. X : 0 1 2 3 4

P(x) : 0 1/30 4/30 9/30 16/30 p.m.f

iii. X : 1 2 3 4 5

P(x) : -1/5 0 1/5 2/5 3/ 5 Not a p.m.f

Continuous Random Variable

Continuous sample space : A sample space is said to be uncountably infinite or continuous if it is not
countable.i.e. It cannot be put into one-one correspondence with the set of positive integers

e.g. Ω = { x | 1< x < 6 }

= { x | x ≥ 10 }

Subsets of continuous interval are called events

Note: The probability of occurrence of individual points must be taken to be zero.i.e. P(X=x) = 0

Continuous random variable: A random variable which takes uncountably infinite values is called a
continuous r.v. i.e. The range set is continuous.

Continuous Probability Distribution

A function f(x) which satisfies the following conditions is called probability distribution of a
continuous r.v:

i. f(x) ≥ 0 for every x Є R

∞
ii. ∫−∞ 𝑓 (𝑥)𝑑𝑥 = 1

The function f(x) is called the probability density function (p.d.f) of X

𝑏
P(a ≤ X ≤ b) = ∫𝑎 𝑓(𝑥) ⅆ𝑥

Ex.1. Let a continuous r.v. X have the following function:

f(x) = 1/5 2<X<7

0 otherwise

i.Verify whether above function is a p.d.f

ii. Find P( 3 < X < 5)

Mean and Variance of X

Let X be a continuous r.v. with p.d.f f(x) and d.f F(x)

∞
Mean(X)= E(X) = ∫−∞ 𝑥𝑓(𝑥) ⅆ𝑥
∞ ∞
Var(X) = E(X2) – E[(X)]2 = ∫−∞ 𝑥 2 𝑓(𝑥) ⅆ𝑥 - [∫−∞ 𝑥𝑓(𝑥) ⅆ𝑥 ]2

Median and Mode of X

If M denotes the median of the distribution then

𝑀 1
P(X≤ M) =1/2 = P(X ≥ M) or F(M) = 0.5 i.e. ∫−∞ 𝑓(𝑥) ⅆ𝑥 =
2

Mode of the distribution is given by f’(x) = 0 and f’’(x) < 0

Distribution Function of a continuous r.v ( c.d.f / d.f )

Let X be a continuous r.v with the p.d.f f(x).

𝑥
A function F(x) = P(X ≤ x) = ∫−∞ 𝑓(𝑡) ⅆ𝑡 is called distribution function or cumulative distribution
function of X. f(t) is the value of the function at x = t

Properties of distribution function:

i. 0 ≤ F(x) ≤ 1

ii. F(x) is a non decreasing function of X. i.e. If x1 ≤ x2 then F(x1) ≤ F(x2)

iii. F(-∞) = 0 and F(∞) = 1

iv. The graph of the distribution function is a smooth unbroken curve

v. f(x) = d/dx F(x)

vi.P(a ≤ X ≤ b) = P(X ≤ b) – P(X ≤ a) = F(b) – F(a)