Anda di halaman 1dari 14

Probability Definitions

1) Classical or Priori definition

3) Relative frequency definition

5) Empirical or Posteriori definition

4) Set theoretic probability definition


1
Classical definition
If an experiment results in ‘n’ exhaustive
mutually exclusive and equally likely cases
and ‘m’ of them are favorable to the
happening of an event E , then probability
p of happening of E is given by
favorable number of cases m

P(E) = p = -------------------------- = ------


exhaustive number of cases n

2
Since number of cases favorable = m
number of cases unfavorable = (n – m)
The prob of happening of E = p = m / n
The prob of not happening = q = (n – m) / n
therefore , p + q = 1
& 0 ≤ p ≤ 1 and 0 ≤ q ≤ 1
E is called certain event if p(E) = 1
E is called impossible event if p(E) = 0

3
Relative frequency defination
With the practical situations , as the number
of trials increased to lager size the
probability is defined as the relative
frequency of occurrences .
P(E) = m / n , for large n

4
Empirical definition
If an experiment is repeated a large number of
times under homogeneous and identical
conditions , then the limiting value of the ratio of
the number of times an event occurs to the
number of trials , as the trials become
indefinitely large is called the probability of
occurrence ( it is assumed that limit is finite )
If in ‘n’ trials an event E occurs ‘m’ times

P(E) = p = Lt m / n
n→∞

5
Set theory approch
Sample Space (S,Ω) : A set of points
representing all possible outcomes
Sample point : An element in S is called a
sample point.
Number of sample points are denoted
by n(S)
An event : Non empty subset of sample
space which satisfies certain conditions .
6
• Mutually exclusive events:
Events A and B are mutually exclusive if
A∩B = Φ
• Complimentary events : denoted by Abar
Defined as set of all points x such that
x belongs to S ,x does not belong to A
• Union of two events:
AUB is set of all points such that x belongs to A
or x belongs to B
• Intersection of two events:
A∩B is set of all points such that x belongs to A
and x belongs to B.
7
Definition of probability

If there are ‘n’ possible , equally likely outcomes of a


random experiment ,the sample space contains n
sample points , the probability associated with
each sample point would be 1/n .
Now if an event A consists of m sample points out of
those n points , then
P(A) = 1/n+1/n +…+ 1/n(m times)
= m/n = n(A) / n(S)
= no of sample pts in A/no of sample pts in S
8
Theorems of probability
• The Addition theorem

• The multiplication theorem

• Bayes theorem for conditional probability

9
Basic probability rules

Addition rule
For simultaneous trials

Mutually exclusive events Partially overlapping events


P(AUB) = P(A)+P(B) P(AUB)=P(A)+P(B)-P(A∩B)

10
Multiplication rule
For consecutive trials

Independent Events Dependent events


P(A∩B) = P(A) x P(B) P(A∩B) = P(A) x P(B/A)

11
• Bayes Rule :
Conditional Probability-Two events A & B are
said to be dependent when B can occur only
when A is known to have occurred and vice
versa . The probability attached to this is called
conditional probability , denoted by P(A/B)
P(AB)
P(A/B) = ------------ - - - - (1)
P(B)
eg. In a sample of 2 defectives in 50 trials
estimate the probability that machine is not
working properly.

12
Let A1and A2 be two mutually exclusive and
exhaustive .
Let B be a sample event which intersects each
A1and A2 , Then
P(A1/B) = P(A1and B) / P(B)
P(A2/B) = P(A2and B) / P(B)
Where
P(B) = P(A1 and B) + P(A2 and B)
And P(A1 and B) = P(A1) x P( B/A1)
P(A2 and B) = P(A2) x P( B/A2)
13
Bayes theorem:
In general if A1,A2,…An are set of n mutually exclusive and
collectively exhaustive events any of which can occur
at the first stage of an experiment followed by
occurrence or nonoccurrence of another event B at the
second stage and the probability of occurrence of B
given that Ai ( i = 1,2…n) has occurred are
P(B/A1),P(B/A2)…P(B/An), then the probability of
occurrence of Ai given that B has occurred are given by
P(Ai) x P( B/Ai)
P(Ai/B) = ------------------------ - - - - -(2)
Σ P(Aj) x P( B/Aj)
(5) Is called the priori prob before revision
(6) Is called the posterior prob revised by making use of
sample information , given by bayesian rule
14

Anda mungkin juga menyukai