Download Week 5, Monday - gozips.uakron.edu

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project

Document related concepts
no text concepts found
Transcript
Chapter 14
Week 5, Monday
Introductory Example
Consider a fair coin:
Question: If I flip this coin,
what is the probability of
observing heads?
Answer: Everyone knows
the answer is 50%, but
let’s look closer at what
this actually means.
Introductory Example
Consider a fair coin:
Trial 1: I flip a coin and
observe a head.
So Far: 100% of my trials
produced heads.
trial
1 2 3 4 5 6
observation H
7 8 9 10
Introductory Example
Consider a fair coin:
Trial 2: I flip a coin and
observe a tail.
So Far: 50% of my trials
produced heads.
trial
1 2 3 4 5 6
observation H T
7 8 9 10
Introductory Example
Consider a fair coin:
Trial 3: I flip a coin and
observe a tail.
So Far: 33% of my trials
produced heads. (this is called
the “relative frequency”)
trial
1 2 3 4 5 6
observation H T T
7 8 9 10
Introductory Example
Consider a fair coin:
How Often is Heads Observed
Relative Frequency
100%
75%
50%
25%
0%
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33
Number of Flips
Probability: Has to do with long-term behavior.
Introductory Example
Consider a fair coin:
How Often is Heads Observed
Relative Frequency
100%
75%
50%
25%
0%
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33
Number of Flips
Law of Large Numbers: For “independent trials”, as the number of trials
increases, the long-run relative frequency gets really close to a single value
(in this case 50%)
Some Vocabulary
Trial 1
Heads
Tails
Trial 2
Heads
Tails
Trial 3
Heads
Tails
Trial: Each occasion upon
which we observe a
random phenomenon
Outcome: The value of
the random
phenomenon
Sample Space: The
collection of all
possible outcomes
More Complicated Example
Consider two fair coins:
Question: If I flip these
coins, what is the
probability of observing
1 head and 1 tail?
Answer: Not as obvious
as before. The true
likelihood is 50%.
More Complicated Example
Consider two fair coins:
Each Trial
Heads, Tails
Tails, Heads
Tails, Tails
Heads, Heads
If either of these two outcomes occur, then
we observed 1 heads and 1 tails
More Complicated Example
Consider two fair coins:
Each Trial
Heads, Tails
Tails, Heads
Tails, Tails
Heads, Heads
We call a group of outcomes an “Event”.
What is the probability of this event?
More Complicated Example
Consider two fair coins:
How Often is '1 head and 1 tail' Observed
Relative Frequency
100%
75%
50%
25%
0%
1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33
Number of Trials
A Nice Assumption
If you assume that every outcome in the sample
space has the same probability of occurring,
then you can calculate the probability of an
event occurring through a formula!
Probability of Event A = (Number of outcomes in A) / (Total number of outcomes)
Each Trial
Heads, Tails
Tails, Heads
Heads, Heads
Tails, Tails
P[1 heads and 1 tails] = 2/4 = 50%
P[at least 1 heads] = 3/4 = 75%
P[no tails] = 1/4 = 25%
Another Example
Consider a fair die:
P[at least 4] = 3/6 = 50%
P[more than 4] = 2/6 = 33%
Each Trial
1
2
3
4
5
6
P[5] = 1/6 = 16.5%
P[either 2, 3, or 6] = 3/6 = 50%
P[more than 2 AND less than 4] = 1/6 = 16.5%
Probability Properties
(1) For any event, “A”,
P[A] is between 0% and 100%
(2) Consider the event, “S”, consisting of all
possible outcomes. P[S]=1
(3) For any event, “A”, consider the event
“not A” (denoted: AC). Then:
P[AC]=100%-P[A]
(4) For any events, “A” and “B”:
P[A or B] = P[A] + P[B] – P[A and B]
Probability Properties
Consider a fair die:
P[1, 2, 3, 4, 5, or 6] = 6/6 = 100%
Each Trial
1
2
3
4
5
6
P[1 or 2] = 2/6 = 33%
P[not {1 or 2}] = P[{1 or 2}C]
= 1 – P[1 or 2]
= 100% – 33%
= 67%
P[{1,2,5,6} or {1,2,3}]
= P[1,2,5,6]+P[1,2,3] - P[{1,2,5,6} and {1,2,3}]
= (4/6) + (3/6) – (2/6)
= 5/6
Related documents