Scribd
Upload
35 views22 pages

Probability Distribution Function-1

Uploaded by

Soumen Kundu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
35 views22 pages

Probability Distribution Function-1

Uploaded by

Soumen Kundu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 22

Probability Distribution

Function

Name : Soumen Kundu


Roll NO : 20101103012
Department : Mechanical Engineering
Subject : Math Assignment
Semester : 3rd
Random variable

 Definition : Let S be a given sample space. Then a real variable X defined on


S is called a random variable. Thus for every point S of a sample space a
unique real value of X i.e. X(s).
 Random variable is two types.
i. Discrete Random Variable
ii. Continuous Random Variable
 Discrete Random variable : If a random variable takes a finite set of values
or countably infinite, it is called Discrete Random Variable.
 Continuous Random Variable : If a random variable assumes an infinite
number of uncountable values, it is called Continuous Random Variable.
Probability Distribution Function

   X be a random variable ( discrete or continuous). The function F defined for all real
Let
x by
:R

[ for discrete variables]

[ for continuous variable]

then F(x) is called Probability Distribution Function.


 Distribution function is also known as cumulative distribution function.
 Domain of F(x) is (
 Range of F(x) is [0,1]
Properties of Distribution Function

  

 If F is the distribution function of the random variable X and if ab, then


P(

Proof:
The event ‘and ‘Xare disjoint and their union is the event ‘ .

[ and are mutually


exclusive events]

  F(X) is monotonically non decreasing function.
If then

Proof:

 F(X) is continuous to the right at every point .


Examples on Distribution Function
  Suppose three coins are thrown. Then the sample space is
S = {HHH, HHT, HTH,THH,HTT,THT,TTH,TTT}
Let X is a random variable and X = number of heads.
X = 0, 1, 2, 3
P(X=0) = p(TTT) =
P(X=1) = P(THT, TTH, HTT) =
P(X=2) = P(HHT, HTH, THH) =
P(X=3) = P(HHH) =

X 0 1 2 3

  Then the probability distribution function is
Necessary & sufficient condition for a function to be
distribution function of a possible random variable :

  Condition:
Any function F(x) with domain R and range a subject of [0,1] is a distribution
function of some random variable X if and only if F(x) be such that,

1.

2. F(x) is monotonically non-decreasing and bounded.

3. F(x) is continuous to the right at all point.

4. F(x) is discontinuous to be the left at every point x=a if P(x=a)>0


Equivalent set / Equipotent set

 Definition:
Two set X and Y are said to be equipotent if there exist a bijection
between them.
 It is denoted by X~Y.
 Two finite set will be equipotent if they have same no. of elements.
 If X and Y are equivalent sets, then they said to have some cardinality.
  Finite set:
A is said to be a finite set if A is equipotent with a finite subset of N.

 Enumerable set:
A is called an enumerable set if A~N.
Example: Z~N, W~N, Q~N.
If A be an enumerable set then the elements of A can be expressed sequentially as

 At most countable:
A set is called At most countable if the set is either finite or enumerable.

 Uncountable:
An uncountable set is an infinite set that contains too many elements to be
countable. It is also known as uncountably infinite set.
Probability Mass Function (p.m.f)
   X be a discrete random variable having X =
Let
as the spectrum

Let being a spectrum point of X.

if x is a spectrum point of X, i.e


Define a function by
0 if x is non-spectrum point

then f is called probability mass function of discrete random variable X.


Necessary & sufficient condition for a
function to be a p.m.f :

  
 [ summation is taken over all the spectrum points ]
  Problem -1 :
Can the following functions be p.m.f ?
a.
2 , x=1/2
f(x) = 1 , x=1/4
0 , elsewhere

Ans :
f(1/2) = 2 but

so f(x) is not p.m.f

b.
0.1 for x =-5
0.5 for x = -1
f(x) = 0.2 for x = 0
0.2 for x = 1
0 elsewhere

Ans:
f(x) ≥ 0 for all values of x

So, f(x) satisfies all the necessary and sufficient conditions. So, f(x) is a p.m.f
 Problem
  -2 :
P.m.f is given by,

X=x 0 1 2 3

P(X=x) k 2k k 3k

Find the value of k ? Also find P(X ≤ 2) and P(1 ≤ X ≤3).

Ans:

or, k+2k+k+3k =1
or, k = 1/7

P(X ≤ 2) = P(0) +P(1) + P(2)


= 1/7 + 2/7 + 1/7
= 4/7

P(1 ≤ X ≤ 3) = P(X ≤ 3) – P(0)


= 1 – 1/7
= 6/7
Probability density function (p.d.f)

  Let X be a continuous random variable with distribution function

Then a function f(x) is said to be probability density function (pdf) of X if f(x) is

integrable on the interval [a,x] for all a and if

This holds for every real x.


Properties of p.d.f
   f(x) is a pdf of a random variable X then
If
i. f(x) ≥ 0 ii.

 As F(x) is a continuous function, so we must have

 For a continuous distribution,

Where f is the probability density function.

 If f(x) is continuous, then from definition of pdf, we have f(x) =F`(x)

 In differential notation we have,

Which is known as the probability differential of X.


  Problem :
The Probability density function of a random variable X is given by
f(x) = k(x-1)(x-2) for 1 ≤ x ≤ 2
Determine,
i. The value of k.
ii. The distribution function
iii. P(5/4 ≤ x ≤ 3/2)
 Ans:
i. Since f(x) is a p.d.f, then
 ii.
The distribution function F(x) is defined by
For x<1 ,

The probability distribution function F:R R is given by


F(x) = 0 if x<1
=
=1 if x>2
iii.
  
Some special type of discrete distribution
  Binomial (n,p) Distribution :

Let X be a discrete random variable. Let and .

Let the spectrum of X be

We say that X has a binomial distribution with parameters n and p if its probability
mass function is
  Poisson (µ) distribution :

It is a distribution related to the probabilities of events which are extremely rare,


but which have a large number of independent opportunities for occurrence.

We got this distribution as limiting case of the binomial distribution by making n


very large and p very small.

Normal binomial distribution


For,

A random variable X whose spectrum is {0,1,2……….} i.e an enumerable set is said to


follow Poisson distribution if its p.m.f is given by,
Some important continuous distribution
 Uniform/Re

You might also like