Professional Documents
Culture Documents
Week 2
Week 2
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 1 / 47
1 Introduction
Motivation
Random Events and Probability
Counting Techniques and Calculation of Probabilities
The conditional probability, independence, and Bayes’ rule
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 2 / 47
Motivation
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 3 / 47
1 Introduction
Motivation
Random Events and Probability
Counting Techniques and Calculation of Probabilities
The conditional probability, independence, and Bayes’ rule
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 4 / 47
Experiment
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 5 / 47
Definitions
Definition
The sample space associated with an experiment is the set consisting of all
possible outcomes. A sample space is also referred to as a probability
space. It is denoted by S.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 6 / 47
Definitions
Definition
An event A is a subset of outcomes in S, A ⊂ S. Event A occurs if the
outcome of the experiment is in A.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 7 / 47
Definitions
Definition
The null subset φ of S is called an impossible event.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 8 / 47
Definitions
Definition
The event A ∪ B consists of all outcomes that are in A or in B or in both
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 9 / 47
Definitions
Definition
The event A ∩ B consists of all outcomes that are in A and B.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 10 / 47
Definitions
Definition
The event AC (the complement of A in S) consists of all outcomes not in
A, but in S.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 11 / 47
Definitions
Definition
Two events A and B are said to be mutually exclusive or disjoint of
A ∩ B = φ.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 12 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 13 / 47
Classical Definition of Probability
Definition
If there are n equally likely possibilities, of which one must occur, and m of
these are regarded as favourable to an event, or as success, then the
probability of the event or a success is given by m/n. The probability of
any event A in the sample space S is denoted by P (A).
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 14 / 47
Frequency Definition of Probability
Definition
The probability of an outcome (event) is the proportion of times the
outcome (event) would occur in a long run of repeated experiments.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 15 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 16 / 47
Frequency Definition of Probability
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 17 / 47
Axiomatic definition of probability
Definition
Let S be a sample space of an experiment. Probability P (·) is a real-valued
function that assigns to each event A in the sample space S a number
P (A), called the probability of A, with the following conditions satisfied:
it is nonnegative, P (A) ≥ 0
it is unity for a certain event. That is, P (S) = 1
it is additive over the union of an infinite number of pairwise disjoint
events, that is, if A1 , A2 , . . . form a sequence of pairwise mutually
exclusive events (Ai ∩ Aj = φ, i 6= j) in S, then:
P∞
P (∪∞ i=1 Ai ) = i=1 P (Ai )
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 18 / 47
Example
A die is loaded (not all outcomes are equally likely) such that the
probability of number i shows up is Ki, i = 1, 2, . . . , 6, and K is a
constant. Find:
I the value of K
I the probability that a number greater than 3 shows up
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 19 / 47
Basic Properties of Probability
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 20 / 47
Example
In a Statistics II class, the Sintesis says that 30% of the students were
in the top 10% of their class and that 40% are economics students, of
whom 15% were in the top 10% of their class. What is the probability
that a student selected randomly from this class either was in the top
10% of their class or an economics student?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 21 / 47
1 Introduction
Motivation
Random Events and Probability
Counting Techniques and Calculation of Probabilities
The conditional probability, independence, and Bayes’ rule
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 22 / 47
Motivation
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 23 / 47
Multiplication principle
Definition
If the experiments A1 , A2 , . . . , Am contain respectively: n1 , n2 , . . . , nm
outcomes, such that for each possible outcomes of A1 there are n2 possible
outcomes for A2 , and so on, then there are a total of n1 , n2 , . . . , nm
possible outcomes for the composite experiments A1 , A2 , . . . , Am .
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 24 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 25 / 47
Sampling with replacement and the objects are ordered
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 26 / 47
Sampling without replacement and the objects are ordered
Let n! be:
n! = n (n − 1) (n − 2) . . . (2) (1)
If r objects are chosen from a set of n distinct objects without
replacement, an ordered arrangement is called a permutation.
Example:
I what is the number of permutation for three letters ABCD?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 27 / 47
Permutation of n object taken m at a time
Theorem
The number of permutations of m objects selected from a collection of n
distincts objects is:
n!
n Pm =
(n − m)!
= n (n − 1) (n − 2) . . . (n − m + 1)
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 28 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 29 / 47
Sampling without replacement and the objects are not
ordered
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 30 / 47
Combinations of n object taken m at a time
Theorem
The number of ways in which m objects can be selected (without
replacement) from a collection of n distinct objects is:
!
n n!
=
m m! (n − m!)
n (n − 1) (n − 2) . . . (n − m + 1)
=
m!
where m = 0, 1, 2, . . . , n.
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 31 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 32 / 47
Example
In an urn containing 9 balls, there are three red balls and 6 blue balls.
We select three balls at random.
I What is the probability that exactly one red ball is selected?
I What is the probability that at most one red ball is selected?
I What is the probability that at least one red ball is selected?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 33 / 47
Example
Suppose that there are 100 economics students and 200 business
students. The BEM board consists of 10 members. What is the
probability that a chosen 10 will have 3 economics students and 7
business students?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 34 / 47
1 Introduction
Motivation
Random Events and Probability
Counting Techniques and Calculation of Probabilities
The conditional probability, independence, and Bayes’ rule
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 35 / 47
Motivation
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 36 / 47
Conditional Probability
P (A ∩ B)
P (A | B) =
P (B)
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 37 / 47
Example
Suppose that you are tossing two dies in sequence. What is the
probability that you see a sum of 8 given that the first die gives you a
face value of 3?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 38 / 47
Some Properties of Conditional Probability
P (A ∩ B) = P (B) P (A | B) = P (A) P (B | A)
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 39 / 47
Example
Suppose that you have basket of 30 green and red apples, of which 10
are green apples. If two fruits are randomly picked in sequence, what
is the probability that both fruits are red apples?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 40 / 47
Two independent events
Definition
Two events A and B with P (A) 6= 0 and P (B) 6= 0 are said to be
independent if
P (A | B) = P (A)
or
P (B | A) = P (B) .
P(A ∩ B) = P(A)P(B)
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 41 / 47
Example
Suppose that we toss two fair dices. Let E1 denote the event that the
sum of the dice is 6 and E2 denote the event that the first die equals
4. Are E1 and E2 independent events?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 42 / 47
Law of Total Probability
Theorem
Assume S = A1 ∪ A2 ∪ . . . ∪ An , where P (Ai ) > 0, i = 1, 2, . . . , n and
Ai ∩ Aj = φ (null set) for i 6= j. Then, for any event B:
n
X
P (B) = P (Ai ) P (B | Ai ) .
i=1
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 43 / 47
Example
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 44 / 47
Bayes’ Rule
Theorem
Assume S = A1 ∪ A2 ∪ . . . ∪ An , where P (Ai ) > 0, i = 1, 2, . . . , n and
Ai ∩ Aj = φ for i 6= j. Then for any event B, with P (B) > 0:
P (Aj ) P (B | Aj )
P (Aj | B) = Pn .
i=1 P (Ai ) P (B | Ai )
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 45 / 47
Example
A a math for economist I class contained 55% male and 45% female
students. At the end of the semester, 3% of males and 10% of
females got an “A/B or above” grade. If one student from this class
is randomly selected and observed to have an “A/B or above” grade,
what is the probability that this is a male student?
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 46 / 47
Steps to apply Bayes’ Rule
Muhammad Ryan Sanjaya (Econ UGM) Statistics II: Lecture 2 February 21, 2020 47 / 47