Anda di halaman 1dari 23

GEC410-

Probability and
Statistics
GEC410-Probability and Statistics Module 1 Lecture
II

Module 1 Lecture II
By

Dr. S. O. Edeki
Department of
By Mathematics,
Covenant
University, Nigeria.

Dr. S. O. Edeki
Department of Mathematics, Covenant University,
Nigeria.

August 22, 2018

1 / 23
GEC410-
Definition: Conditional Probability Probability and
Statistics

Module 1 Lecture
II
Let A and B be two events ( not necessarily from the same
experiment, the conditional probability of A given that B has
already occurred, written as P(A, givenB) or P(A | B) is By
defined as:
Dr. S. O. Edeki
Department of
Mathematics,
P(A ∩ B) Covenant
P(A | B) = , P(B) > 0. University, Nigeria.
P(B)

Note: the line in P(A | B) is vertical not slant.


Similarly,

P(A ∩ B)
P(B | A) = , P(A) > 0.
P(A)

2 / 23
GEC410-
Definition: Dependent (Independent) Events Probability and
Statistics

Module 1 Lecture
II

Two or more events are said to be dependent if the


By
occurrence of one affects the occurrence of the others. For
instance, suppose it is planned to draw two balls from a bag Dr. S. O. Edeki
Department of
of 20 balls, if a ball is drawn without replacement, and the Mathematics,
Covenant
second ball is drawn, thus, the event of drawing the second University, Nigeria.
ball is dependent on that of the first ball.
A and B are independent if:

P(A | B) = P(A)

3 / 23
GEC410-
Remarks & examples on independent events Probability and
Statistics

Module 1 Lecture
II

For independent events A and B, we have:


By
i) P(A | B) = P(A)
ii) P(B | A) = P(B) Dr. S. O. Edeki
Department of
Exercise: Show that P(A ∩ B) = P(A).P(B). If A and B Mathematics,
Covenant
are two independent events. University, Nigeria.
Example 2: Find (i) P(B) and (ii)P(A ∪ B) if A and B are
1 1
independent events such that P(A) = , P(A ∩ B) = .
3 12
1 1
Ans: (i) P(B) = (ii) P(A ∪ B) =
4 2

4 / 23
GEC410-
Exercise: independent events Probability and
Statistics

Module 1 Lecture
II

By

The events A and B are such that Dr. S. O. Edeki


P(A | B) = 0.4, P(B | A) = 0.25 and P(A ∩ B) = 0.12. Department of
Mathematics,
Covenant
i Find P(B) University, Nigeria.

ii Give a reason why A and B are not independent.

5 / 23
GEC410-
Examples: Conditional Probability Probability and
Statistics

Module 1 Lecture
II
Let M, R, C , and F be certain events with the detail in the
table below:
By
R C
Dr. S. O. Edeki
M 7 5 12 Department of
Mathematics,
F 3 10 13 Covenant
University, Nigeria.
10 15 25

Find (i) P(F∩R), (ii)P(R), and(iii)P(F | R)

3 2 3
(i) , (ii) , (iii)
25 5 10

6 / 23
GEC410-
Examples: Conditional Probability Probability and
Statistics

Module 1 Lecture
II

By
Example 1
Dr. S. O. Edeki
In a particular clinic, a lab attendant attended to 100 Department of
patients with the following detail: for the male patients, 40 Mathematics,
Covenant
are tall while 30 are short. For the female patients, 20 are University, Nigeria.

tall while 10 are short. Suppose a patient is selected at


random, what is the probability that he is tall if he is a male?

7 / 23
GEC410-
Ex: Conditional Probability Probability and
Statistics

Module 1 Lecture
II

Example/Classwork 2:
By
Let the accommodation status of students be classified as
either ‘resident’ or ‘off campus’. Out of a group of 25 Dr. S. O. Edeki
students, 7 are male ‘residents’, 10 are female ‘off campus’ Department of
Mathematics,
and 12 are males. Calculate the probability that a name Covenant
University, Nigeria.
chosen at random from a list of these students is that of:
(i) A female resident.
(ii) A resident.
(iii) A female, given that the student is ‘resident’.

8 / 23
GEC410-
Ex: Conditional Probability Probability and
Statistics

Module 1 Lecture
II

By
Ex/ classwork 3
The probability that a man is in his office when a salesman Dr. S. O. Edeki
Department of
calls is 0.6. Given that the man is in his office when the Mathematics,
Covenant
salesman calls, the probability that he makes a purchase is University, Nigeria.

0.4. What is the probability that the man is in his office and
makes a purchase when the salesman calls?
Ans: 0.24

9 / 23
GEC410-
Bayes Theorem Probability and
Statistics

Module 1 Lecture
II

Bayes theorem considers further application of the concept


of conditional probability. By
Theorem
Let B1 , B2 , B3 , ..., Bn form a partition of a sample space S, Dr. S. O. Edeki
Department of
and A ⊆ S.Then Mathematics,
Covenant
University, Nigeria.
a TheoremPof total probability:
P(A) = ni=1 P(Bi ).P(A | Bi )
b Bayes Theorem:
P(Bj ).P(A|Bj )
P(Bj | A) = Pn P(B i ).P(A|Bi )
i=1

Proof: Classwork / Exercise

10 / 23
GEC410-
Bayes Theorem Probability and
Statistics

Module 1 Lecture
II
Examples on Bayes Theorem
1 (i) In a certain system factory, machines A, B and C
manufacture 25, 35 and 40 percent of the total output By

respectively. Of their output, 5, 4, and 2 percent Dr. S. O. Edeki


respectively are defective systems. All the system Department of
Mathematics,
produced in the factory are put into one store. Covenant
University, Nigeria.
a) Find the probability that one system chosen at
random from the store is defective.
b) A system is chosen at random from the store and
found to be defective. What is the probability that it
was manufactured by Machine B?
69 28
Ans: (a.) (0.0345) (b.) (0.4059)
2000 69
11 / 23
GEC410-
Example 2: on Bayes Theorem Probability and
Statistics

Module 1 Lecture
A computer program generates random questions in II
arithmetic that children have to answer within a fixed time.
The probability of the first question being answered correctly
is 0.8. Whenever a question is answered correctly, the next By

question generated is more difficult, and the probability of a Dr. S. O. Edeki


correct answer being given is reduced by 0.1. Whenever a Department of
Mathematics,
question is answered wrongly, the next question is of the Covenant
University, Nigeria.
same standard, and the probability of a correct answer being
given remains unchanged. Find:
a The probability that the second question is answered
correctly.
b The probability that the second question is answered
correctly given that the third question is answered
correctly.
Ans: (a) 0.72 (b) 0.69
12 / 23
GEC410-
Probability Distribution Probability and
Statistics

Module 1 Lecture
II

By

A probability distribution provides the possible values of the Dr. S. O. Edeki


Department of
random variable and their corresponding probabilities. Mathematics,
Covenant
A probability distribution can be in the form of a table, University, Nigeria.

graph or mathematical formula.

13 / 23
GEC410-
Random variable and Probability Distribution Probability and
Statistics

Module 1 Lecture
II

Let S be the sample space of a random experiment. Then, a


real valued function X defined on S is called a random By

variable.
Dr. S. O. Edeki
Mathematically, X : S → R. Department of
Mathematics,
Thus, a probability distribution gives the probability of each Covenant
University, Nigeria.
possible value of a variable.
Probability distribution ( function) is of TWO types
depending on the nature of the random variable.
Hence: For discrete random variable, we have probability
mass function (pmf), and probability density function (pdf)
for continuous random variable.

14 / 23
GEC410-
Constructing probability distribution Probability and
Statistics

Module 1 Lecture
II

By
Example: If two coins are tossed once, the associated sample
space is: Dr. S. O. Edeki
Department of
Mathematics,
Covenant
University, Nigeria.
S = {HH, HT , TH, TT }.

Find probability distribution with relation to number of


heads.

15 / 23
GEC410-
Properties of p.m.f Probability and
Statistics

Module 1 Lecture
II

By

Let X be a discrete random variable with possible values Dr. S. O. Edeki


x1 , x2 , ...xn . Then Department of
Mathematics,
Covenant
i P(X = xi ) = pi ≥ 0, i = 1(1)n. University, Nigeria.
Pn
ii i=1 Pi = 1 ( legitimate pmf)

16 / 23
GEC410-
Example 1: Properties of p.m.f Probability and
Statistics

Module 1 Lecture
II
Let X be a discrete random variable with the following
probability distribution:
By
X=x -3 -2 -1 0 1
P(X=x) 0.1 0.25 0.3 0.15 c Dr. S. O. Edeki
Department of
Mathematics,
Covenant
Find: University, Nigeria.

a The value of c.
b P(−3 ≤ X < 0)
c P(X > −1)
d P(−1 < X < 1)
Ans: (a)0.2 (b) 0.65 (c) 0.35 (d) 0.15 .

17 / 23
GEC410-
Ex: Properties of p.m.f Probability and
Statistics

Module 1 Lecture
II
Suppose the random variable X has values 1, 2, 3... and that
1 By
P(X = Xi ) = , i = 1, 2, 3, ...
2i
. Dr. S. O. Edeki
Department of
Mathematics,
a Verify that pi is a legitimate pmf. Covenant
University, Nigeria.
b Compute the probability that X is even.
c Compute P(X ≥ 3).

1 1
(a)sum to be 1, (b) , (c)
3 4

18 / 23
GEC410-
Examples of discrete distributions Probability and
Statistics

Module 1 Lecture
II

By
Examples of discrete density function are:
Dr. S. O. Edeki
Bernoulli trials, Department of
Mathematics,
Binomial distribution, Covenant
University, Nigeria.

Poisson distribution,
Geometric distribution and so on.

19 / 23
GEC410-
The pmf discrete r.v I Probability and
Statistics

Module 1 Lecture
II
1 Bernoulli distribution

By
p k q n−k ,

k = 0, 1
P(X = k) = p(k) =
0, otherwise. Dr. S. O. Edeki
Department of
Mathematics,
Covenant
2 Binomial distribution (X ∼ b(n, p)) University, Nigeria.

 n
Ck p k q n−k , k = 0, 1, 2, ...
P(X = k) = p(k) =
0, otherwise.

Note p + q = 1
For the binomial distribution:
Mean = np
Variance = npq.
20 / 23
GEC410-
The pmf discrete r.v II Probability and
Statistics

Module 1 Lecture
II

By
3 Poisson Distribution
 Dr. S. O. Edeki
 λk e −λ Department of

P(X = k) = p(k) = , k = 0, 1, 2, ... λ > 0 Mathematics,


Covenant
k!
 0, otherwise. University, Nigeria.

For Poisson Distribution.

21 / 23
GEC410-
Continuous random variable Probability and
Statistics

Module 1 Lecture
II

By
A random variable X is continuous if there exists a Riemann
integrable function f (x) satisfying the following conditions: Dr. S. O. Edeki
Department of
i f (x) > 0 ∀x ∈ R Mathematics,
R∞ Covenant
University, Nigeria.
ii −∞ f (x)dx = 1
iii for all a, b ∈ R, ∃a
R b< b, s. t.
P(a ≤ x ≤ b) = a f (x)dx.

22 / 23
GEC410-
References Probability and
Statistics

Module 1 Lecture
II

1 P. N. Okonta (2000): Fundamental of probability By


theory, Functional publishing company, Nigeria.
Dr. S. O. Edeki
2 J. Crawshaw and J. Chamber (2001): A concise course Department of
Mathematics,
in advance level statistics Stanley Thomas, 4th ed. UK. Covenant
University, Nigeria.
3 B. D. Gupta (2004): Mathematical physics, 3rd ed.
UBS publishers, New Delhi.
4 K. F. Riley, M. P. Hobson, and S. J. Bence (1998),
Cambridge Uni. Press.

23 / 23

Anda mungkin juga menyukai