Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
4 views

3. introduction to probability

This document serves as an introduction to probability theory, outlining essential concepts such as random experiments, sample spaces, events, and their relationships including intersection, union, and complements. It discusses probability postulates, conditional probability, statistical independence, and the Bayes' theorem, providing examples to illustrate these concepts. The document emphasizes the importance of probability in statistical modeling and estimation.

Uploaded by

Eren Bayri
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views

3. introduction to probability

This document serves as an introduction to probability theory, outlining essential concepts such as random experiments, sample spaces, events, and their relationships including intersection, union, and complements. It discusses probability postulates, conditional probability, statistical independence, and the Bayes' theorem, providing examples to illustrate these concepts. The document emphasizes the importance of probability in statistical modeling and estimation.

Uploaded by

Eren Bayri
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 18

STAT 410

Statistics
Introduction to Probability

Sait Çakır
Yeditepe University
Important terms
• Why to study the probability theory?
- An essential building block for inductive statistics
- Provides us with stochastic models and limit theorems (important tools for making estimations)
- Model uncertainty with the help of probability theory

• Basic concepts
- Random experiment: a process leading to an uncertain outcome
- Basic outcome: a possible outcome of a random experiment
- Sample space: the collection of all possible outcomes of a random experiment
- Event: any subset of basic outcomes from the sample space

Example: Flip a coin twice -> a random experiment


- The sample space -> Each element in the set is a basic outcome
- Define an event A: at least one of the outcomes is a tails ->
- Important to note:
Important terms
• Intersection of events: If A and B are two events in a sample space S, then the intersection, , is the set
of all outcomes in S that belong to both A and B
- consists of common elements to both sets
- means that both A and B occur together

Example: Define the event B: at least one of the outcomes is a heads

• A and B are Mutually Exclusive Events if they have no basic outcomes in common
- -> No common element to both sets
- They are represented by disjoint sets

Example: Define the event C: the first outcome is a heads, and the event D: both outcomes are tails

- If one of these events occur, the other one cannot!


Important terms
• Union of events: If A and B are two events in a sample space S, then the union, , is the set of
all outcomes in S that belong to either A or B
- means that at least one of these event occurs

Example:

• Events are Collectively Exhaustive events if


- Their union covers the whole sample space

Example:

• The Complement of an event A is the set of all basic outcomes in the sample space that do not
belong to A. The complement is denoted by
Example
We know that that it will take no more than 7 days to install a machine after its purchase
Let A be the event “it will be more than 4 days before the machinery becomes available” and B be the event “it will be less than 6 days
before the machinery becomes available.”
Sample space: -> The day the machine will operate

a. Describe the event that is the complement of event A.

b. Describe the event that is the intersection of events A and B.

c. Describe the event that is the union of events A and B.

d. Are events A and B mutually exclusive?


No, since
e. Are events A and B collectively exhaustive?
Yes, since
f. Show that

g. Show that
Probability and its postulates
• Probability: the chance that an uncertain event will occur
-

• Classical probability: based on the assumption that all basic outcomes in the sample space
have the same chance of occurrence
Then

Discussion: Does mean that A is an impossible event?


No! Define A: Arda Guler will score a goal at the minute 89. A goal can be scored at any moment
between the minute 0 and 90. There are uncountably many values in the and the minute 89
sharp is just one of them. So . But, Arda can of course score a goal at the minute 89 sharp so it is
not an impossible event
Counting the possible outcomes
The classical probability requires a count of the outcomes in the sample space

• The mathematical problem: How many different ways are there to choose k objects out of n distinct
objects?
- The ordering of objects matters, and we draw them with replacement

- The ordering of objects matters, and we draw them without replacement

where
the number of possible arrangements when k objects are to be selected from a total of n objects and
arranged in order [with (n – k) objects left over]
- The ordering of objects does not matter, and we draw them without replacement

The number of combinations of k objects chosen from n is the number of possible selections that can be made
Permutations and combinations example
Suppose that two letters are to be selected from A, B, C, D and arranged in order.

• How many permutations are possible?

The permutations are


AB AC AD BA BC BD
CA CB CD DA DB DC
• How many combinations are possible (i.e., order is not important)?

The combinations are


AB (same as BA) BC (same as CB)
AC (same as CA) BD (same as DB)
AD (same as DA) CD (same as DC)
Probability postulates
i) If A is an event in the sample space, that is, , then
ii) If A is an event in the sample space, that is, , and denote the basic outcomes, then
iii)

• Complement rule:

• Addition rule:
Conditional probability
• We secure an information that the event A has occurred. How to make use of this info to
improve the precision of our probability calculations?
- We should update the probabilities of the remaining events
- Prior to the info, our sample space was . After the info, A will be our new sample space

• Definition: Let A be an event such that P(A) > 0 and . Then,

is called the conditional probability of B on condition A.


Corollary: = – multiplication rule
And similar reasoning also yields
=
Conditional probability example
A fair die is rolled once. Let X be the result of the roll. Let A: {X=6} and B: {X>4}. ?

. Since
Additional considerations
since by probability axioms
• For disjoint sets, = , ?

• The usage of complement rule: vs


A change in the condition is not allowed:

• What about
given that
Statistical independence
If the probability of one event does not change regardless of the other event occurs or not, then
they are said to be statistically independent

Definition:

given that

Simple test: A and B are independent events if =


Example
• Rolling a fair die. Let X be the result of the roll.
Consider the events A: {X =1,3,5} and B: {X= 1, 2, 3, 4}.
Are A and B independent?
Example
• Interchanging the roles

Let W: being wet, S: swimming

. What about Is it also equal to 1?

• So, usually
The Bayes’ theorem
• The Bayes’ theorem is based on the idea of reversing the conditioning

• Given that,

Proof. [Hint: Consider]


The Bayes’ theorem
• Use the fact that
A = () () P(A) = P() P()
= +

• Thus, we have
• To generalize: If we partition the whole sample space into N 2
disjoint sets , then
for any j
given that
Example
• 1% of women who participate in routine screening have breast
cancer. 80% of women with breast cancer will get positive
mammographies. 9.6% of women without breast cancer will also get
positive mammographies. A woman had a positive mammography in
a routine screening. What is the probability that she actually has
breast cancer?

You might also like