Date post: | 01-Feb-2016 |
Category: |
Documents |
Upload: | donald-yum |
View: | 218 times |
Download: | 0 times |
1
Chapter 4
Basic Probability
David Chow
Sep 2014
2
Learning Objectives
In this chapter, you will learn:
Basic probability concepts,
Conditional probability, and
Bayes’ Theorem.
3
Definitions
Probability: the chance that an event will
occur, and 0 ≤ P ≤ 1
Event: Each possible type of outcome
Simple Event: an event that can be described
by a single characteristic
Sample Space: the collection of all possible
events
4
Three Probability Approaches
1. a priori classical probability:
based on prior knowledge of the
process involved.
2. empirical classical probability:
based on observed data.
3. subjective probability: based on
individual judgment (which may
come from past experience, personal
opinion, or analysis of a particular
situation).
Eg: A sailor assessing the probability
of raining is an example of ___.
5
Classical Probability
Calculating classical probability
1. a priori classical probability
2. empirical classical probability
outcomes possible ofnumber total
occurcan event the waysofnumber Occurrence ofy Probabilit
T
X
observed outcomes ofnumber total
observed outcomes favorable ofnumber Occurrence ofy Probabilit
6
Classical Probability
Two assumptions on classical probability
1. All outcomes are equally likely.
2. A procedure is repeated again and again, so
that the relative frequency probability (the
formulae on the previous slide) of an event
tends to approach the actual probability.
- This is called the Law of Large Numbers
- Probability is essentially a proportion
7
Eg: A Priori Classical Probability
Find the probability of selecting a face card (Jack, Queen,
or King) from a standard deck of 52 cards.
cards ofnumber total
cards face ofnumber Card Face ofy Probabilit
T
X
13
3
cards total52
cards face 12
T
X
8
Eg: Empirical Classical Probability
Taking Stats Not Taking Stats Total
Male 84 145 229
Female 76 134 210
Total 160 279 439
Find the probability of selecting a male taking statistics
from the population described in the following table:
191.0439
84
people ofnumber total
stats takingmales ofnumber Stats Taking Male ofy Probabilit
9
Eg: Sample Space
The Sample Space is the collection of all possible
events
Eg1: All 6 faces of a die:
Eg2: All possible outcomes when having a child: Boy or Girl
10
Events in Sample Space
Simple event
An outcome with one characteristic
Eg: A diamond card from a deck of cards
Complement of an event A (denoted A/)
All outcomes that are not part of event A
Eg: All cards that are not diamonds
Joint event
Involves two or more characteristics simultaneously
Eg: An ace that is also red from a deck of cards
11
Visualizing Events in
Sample Space
Contingency Tables:
Tree Diagrams:
Ace Not Ace Total
Black 2 24 26
Red 2 24 26
Total 4 48 52
Full Deck
of 52 Cards Sample
Space
2
24
2
24
12
Simple vs. Joint Probability
Simple (Marginal) Probability refers to the
probability of a simple event.
Eg: P(King)
Joint Probability refers to the probability of
an occurrence of two or more events.
Eg: P(King and Spade)
13
Mutually Exclusive Events
Mutually exclusive events are events that cannot occur
together (simultaneously).
Eg1: Drawing a card
A = queen of diamonds; B = queen of clubs
Events A and B are mutually exclusive if one card is selected
Eg2: New-born baby
B = having a boy; G = having a girl
Events B and G are mutually exclusive if one child is born
14
Collectively Exhaustive Events
Collectively exhaustive events
The set of events covers the entire sample space
Hence, one of the events must occur
Eg: A deck of cards
A = aces; B = black cards; C = diamonds; D = hearts
Events A, B, C and D are collectively exhaustive (but not mutually exclusive – a selected ace may also be a heart)
Events B, C and D are collectively exhaustive and also mutually exclusive
15
Computing Joint and
Marginal Probabilities
The probability of a joint event, A and B:
Computing a marginal (or simple) probability:
Where B1, B2, …, Bk are k mutually exclusive and collectively exhaustive events
outcomeselementaryofnumbertotal
BandAsatisfyingoutcomesofnumber)BandA(P
)BandP(A)BandP(A)BandP(AP(A) k21
Eg: B = Colleges
16
Joint Probability Using a
Contingency Table
P(A1 and B2) P(A1)
Total Event
P(A2 and B1)
P(A1 and B1)
Event
Total 1
Joint Probabilities Marginal (Simple) Probabilities
A1
A2
B1 B2
P(B1) P(B2)
P(A2 and B2) P(A2)
17
Eg: Joint Probability
P (Red and Ace)
52
2
cards of number total
ace and red are that cards of number
Ace Not
Ace
Total
Black 2 24 26
Red 2 24 26
Total 4 48 52
18
Eg: Marginal (Simple) Probability
P(Ace)
52
4
52
2
52
2)BlackandAce(P)dReandAce(P
Ace Not Ace Total
Black 2 24 26
Red 2 24 26
Total 4 48 52
19
Probability Summary So Far
What does “P (head) = ½” mean?
There must be a head out of the next 2 tosses.
The result must be head or no head, so P (head) must be either 1 or 0.
True or False?
Probability measures the likelihood that an event will occur.
0 ≤ P(A) ≤ 1 for any event A.
The sum of the probabilities of all mutually exclusive and collectively exhaustive events is 1.
P(A) + P(B) + P(C) = 1
A, B, and C are mutually exclusive and collectively exhaustive
Marginal probability = sum of joint probabilities if ____
Certain
Impossible
0.5
1
0
20
General Addition Rule
P(A or B) = P(A) + P(B) - P(A and B)
General Addition Rule:
If A and B are mutually exclusive, then
P(A and B) = 0, so the rule can be simplified:
P(A or B) = P(A) + P(B)
for mutually exclusive events A and B
21
Eg: General Addition Rule
Taking Stats Not Taking Stats Total
Male 84 145 229
Female 76 134 210
Total 160 279 439
Find the probability of selecting a male or a statistics student
from the population described in the following table:
P(Male or Stat) = P(M) + P(S) – P(M or S)
= 229/439 + 160/439 – 84/439 = 305/439
22
Eg: Titanic Mortality
1. P (a man or a boy) =
2. P (a man or a survivor) =
Men Women Boys Girls Total
Survived 332 318 29 27 706
Died 1360 104 35 18 1517
Total 1692 422 64 45 2223
23
Conditional Probability
24
Case Study: Genius & Maniac
Aristotle: There is no great genius without a mixture of madness
Scientists at King’s College London found that
Top graders at school were four times more likely to develop bipolar disorder (manic depression) than average students
The link was strongest among those who studied music or literature
25
Conditional Probability
A conditional probability is the probability of one event, given that another event has occurred:
P(B)
B)andP(AB)|P(A
P(A)
B)andP(AA)|P(B
where P(A and B) = joint probability of A and B,
P(A) = marginal probability of A, and P(B) = marginal probability of B
The Venn diagram provides an intuitive explanation.
The conditional
probability of A given
that B has occurred
The conditional
probability of B given
that A has occurred
26
Eg: Conditional Probability
Of the cars on a used car lot, 70% have air conditioning (AC) and 40% have a CD player (CD). 20% of the cars have both.
What is the probability that a car has a CD player, given that it has AC ?
I.e., find P(CD | AC).
27
Eg: Conditional Probability
CD No CD Total
AC 0.2 0.5 0.7
No
AC
0.2 0.1 0.3
Total 0.4 0.6 1.0
.2857.7
.2
P(AC)
AC)andP(CDAC)|P(CD
Given AC, we only consider the top row (70% of the cars). Of these, 20% have a CD player. 20% of 70% is about 28.57%.
28
Eg: Conditional Probability in
Decision Trees
P(CD and AC) = .2
P(CD and AC/) = .2
P(CD/ and AC/) = .1
P(CD/ and AC) = .5
4.
2.
6.
5.
6.
1.
All
Cars
4.
2.
Given CD or
no CD:
29
Eg: Conditional Probability in
Decision Trees
P(AC and CD) = .2
P(AC and CD/) = .5
P(AC/ and CD/) = .1
P(AC/ and CD) = .2
7.
5.
3.
2.
3.
1.
All
Cars
7.
2.
Given AC or
no AC:
30
Eg: Card Counting
What is the probability of
getting a high-valued card?
David Ho (何大一)
David Ho is a famous researcher of AIDS for the “AIDS cocktail” treatment
Movie: 21
Inspired by the true story of the MIT Blackjack Team, which is split into two groups:
1. "Spotters" play the minimum bet and do the counting. They send secret signals to the "big players“
2. “Big players“ place large bets when the count is favorable
31
Statistical Independence
Two events are independent if and only if:
Events A and B are independent when the
probability of one event is not affected by the
other event.
P(A)B)|P(A
32
Eg: Titanic Mortality Again
Probability of getting a women or child if a survivor
is randomly selected
P(man | died) =
Are the events “man” and “died” statistically
independent?
Men Women Boys Girls Total
Survived 332 318 29 27 706
Died 1360 104 35 18 1517
Total 1692 422 64 45 2223
33
Eg1: Statistical Independence
Given the following contingency table:
What is the probability of
(a) A|B ?
(b) A’|B’?
(c) A|B’ ?
(d) Are events A and B statistically independent?
B B’
A 10 30
A’ 25 35
34
Multiplication Rule
Multiplication rule for two events A and B:
If A and B are independent, then
and the multiplication rule simplifies to:
P(B)B)|P(AB)andP(A
P(B)P(A)B)andP(A
P(A)B)|P(A
35
Multiplication Rule
P (A and B) is the product of the probability
of event A and the probability of event B.
But the probability of B has to take into
account the previous occurrence of event A.
Hence the conditional probability P(B|A)
appears in the multiplication rule.
36
Multiplication Rule
Eg: Find P (2 and 2) if a die is rolled twice
Eg: Find P (2 Aces) if two cards are drawn
from a deck
with replacement or
without replacement
37
Multiplication Rule
Statistical independence simplifies the multiplication
rule, but sampling without replacement implies
dependence.
General rule: Assume stat. independence when
sample size (n) is within 5% of the population (N),
i.e., n =< 0.05 (N)
Eg: A sample of 12 camera are drawn from a population
of 1,000.
Given a 5% defect rate, find P (all 12 cameras are good).
38
Eg: Multiplication Rule
Suppose a city council is composed of 5
democrats, 4 republicans, and 3 independents.
Find the probability of randomly selecting a
democrat followed by an independent.
Note that after the democrat is selected (out of 12
people), there are only 11 people left in the
sample space.
.1145/442)(3/11)(5/1 P(D)D)|P(ID)and P(I
39
Marginal Probability Using
Multiplication Rules
)P(B)B|P(A)P(B)B|P(A)P(B)B|P(A P(A) kk2211
Marginal probability for event A:
Where B1, B2, …, Bk are k mutually exclusive and collectively exhaustive events
40
Bayes’ Theorem
Bayes’ Theorem was developed by Thomas
Bayes in the 18th Century.
It is used to revise previously calculated
probabilities based on new information.
It is an extension of conditional probability.
41
Bayes’ Theorem
))P(BB|P(A))P(BB|P(A))P(BB|P(A
))P(BB|P(AA)|P(B
kk2211
iii
where:
Bi = ith event of k mutually exclusive
and collectively exhaustive events
A = new event that might impact P(Bi)
42
Eg: Bayes’ Theorem
A drilling company has estimated a 40% chance of striking
oil for their new well. A detailed test has been scheduled for
more information.
Historically,
60% of successful wells have had detailed tests, and
20% of unsuccessful wells have had detailed tests.
Given that this well has been scheduled for a detailed test,
what is the probability that the well will be successful?
43
Eg: Bayes’ Theorem
Let S = successful well, U = unsuccessful well
P(S) = .4 , P(U) = .6 (prior probabilities)
Define the detailed test event as D
Conditional probabilities:
P(D|S) = .6 P(D|U) = .2
Find P(S|D)
44
Eg: Bayes’ Theorem
667.12.24.
24.
)6)(.2(.)4)(.6(.
)4)(.6(.
U)P(U)|P(DS)P(S)|P(D
S)P(S)|P(DD)|P(S
Apply Bayes’ Theorem:
So, the revised probability of success, given that this well has been scheduled for a detailed test, is .667
45
Eg: Bayes’ Theorem
Given the detailed test, the revised probability of a
successful well has risen to .667 from the original estimate
of 0.4.
Event Prior
Prob.
Conditional
Prob.
Joint
Prob.
Revised
Prob.
S (successful) .4 .6 .4*.6 = .24 .24/.36 = .667
U (unsuccessful) .6 .2 .6*.2 = .12 .12/.36 = .333
46
Review
47
Eg2: Addition Rule
P (planned to purchase) =
P (planned or actually purchased) =
Use the contingency table in this example to illustrate the addition rule.
Actually purchased
Planned to purchase Yes No Total
Yes 200 50 250
No 100 650 750
Total 300 700 1000
48
Eg3: Statistical Independence
A sample of 600 respondents was selected in Beijing to study
consumer behavior, with the following results:
Enjoys Shopping Gender
For Clothing Male Female Total
Yes 163 269 432
No 125 43 168
Total 288 312 600
49
Eg3: Continued
(a) Suppose the respondent chosen is a female. What is the probability that she does not enjoy shopping for clothing?
(b) Suppose the respondent chosen enjoys shopping for clothing. What is the probability that the individual is a male?
(c) Are enjoying shopping for clothing and the gender of the individual statistically independent? Explain.
50
Eg4: Bayes’ Theorem
1. If P(B) = 0.05, P(A | B) = 0.80, P(B’) = 0.95, and P(A | B’) = 0.40, find P(B | A).
2. An advertising executive is studying television viewing habits of married men and women during prime-time hours.
Based on past viewing records, the executive has determined that during prime time, husbands are watching television 60% of the time. When the husband is watching television, 40% of the time the wife is also watching. When the husband is not watching television, 30% of the time the wife is watching television.
Find the probability that
(a) If the wife is watching television, the husband is also watching television.
(b) The wife is watching television in prime time.
51
Video
52
賭仔自嘆 鄭君綿 1969
拎LUM六 長衫六
高腳七 仲有一隻大頭六
二三更 瓜老襯 輸到我木
日夜賭場黎侍候 生意唔撈我兩頭游
我o既錢輸晒 真係冇修
食梗青 頂肚癮 搵菜頭
畫則又怕彈番轉頭
問人地借 佢又拎下拎下頭
籌碼部佢又詐嬲 LEAM出碼頭把盤收
爛手錶 都當晒 HAM BAN LAN冇謀
祖先不開眼 令我好擔憂
我從前知道係咁醜 我都唔使MOU街頭
http://hk.youtube.com/watch?v=eN68W2fWwR0&feature=related
53
內地歹徒拍片推銷六合彩騙局
蘋果日報 2011-05-08
內地歹徒拍片推銷六合彩騙局 遭冒名欺詐馮程淑儀無奈
http://www.youtube.com/watch?v=Np4adVu-om0
六合彩在內地的地下賭風猖獗,不少人迷信六合彩貼士。
不法之徒假扮香港高官及賽馬會高層,拍攝宣傳片聲稱有方法可預測本港六合彩結果,在網上散播,引誘不知情內地人,入會購買所謂的「中獎號碼」。
馬會已報警,並要求有關網站刪除片段。警方表示正跟進事件。