Upload
william-teo
View
218
Download
0
Embed Size (px)
Citation preview
8/3/2019 BM6043_Probability
1/50
Methods of Assigning Probabilities
8/3/2019 BM6043_Probability
2/50
Methods to Assigning Probabilities
There are three ways to assign a probability, P(E), to anevent, E, namely:
Classical approach: assigning probabilities based on lawsand rules and present in the form of ratio or fraction.
Relative frequency: assigning probabilities based oncumulated historical data: frequency an event occurred in the
past / total number of opportunities for the event to haveoccurred.
Subjective approach: Assigning probabilities based on theassignors (subjective) judgment.
8/3/2019 BM6043_Probability
3/50
Classical Approach
If an experiment has n possible outcomes, this methodwould assign a probability of 1/n to each outcome. It is
necessary to determine the number of possible (collectively
exhaustive) events/outcomes.
Experiment: Rolling adieOutcomes {1, 2, 3, 4, 5, 6}
Probabilities: Each sample point has a 1/6 chance of
occurring.
8/3/2019 BM6043_Probability
4/506.4
Classical Approach
Experiment: Rolling two dice and observing the totalOutcomes: {2, 3, , 12}
Examples:
P(2) = 1/36
P(6) = 5/36
P(10) = 3/36
1 2 3 4 5 6
1 2 3 4 5 6 7
2 3 4 5 6 7 8
3 4 5 6 7 8 9
4 5 6 7 8 9 10
5 6 7 8 9 10 11
6 7 8 9 10 11 12
8/3/2019 BM6043_Probability
5/506.5
Relative Frequency Approach
UMS Computer Shop tracks the number of tablet PC it sellsover a month (30 days):
For example,
10 days out of 30
2 units were sold.
From this we can constructthe probabilities of an event
(i.e. the # of tablet PC sold on a given day)
Tablet PC Sold # of Days
0 1
1 22 10
3 12
4 5
8/3/2019 BM6043_Probability
6/506.6
Relative Frequency Approach
There is a 40% chance UMS Computer will sell 3 desktops
on any given day
Tablet PC Sold # of Days Tablet PC Sold
0 1 1/30 = .03
1 2 2/30 = .07
2 10 10/30 = .33
3 12 12/30 = .404 5 5/30 = .17
= 1.00
8/3/2019 BM6043_Probability
7/506.7
Subjective Approach
Not a scientific approach.
Probability comes from persons intuition or reasoning.
Based on the feelings or insights of the person determiningthe probability.
Examples of subjective probability?
Is it reliable?
8/3/2019 BM6043_Probability
8/506.8
Joint, Marginal, Conditional Probability
Methods to determine probabilities of events that result fromcombining other events in various ways.
There are several types of combinations and relationships
between events:
Complement eventIntersection of events
Union of events
Mutually exclusive events
Dependent and independent events
8/3/2019 BM6043_Probability
9/50
Complement of an Event
Thecomplement of event A is defined to be the eventconsisting of all sample points that are not in A.
Complement of A is denoted by Ac (or A')
The Venn diagram below illustrates the concept of acomplement.
P(A) + P(Ac ) = 1 A Ac
8/3/2019 BM6043_Probability
10/506.10
Complement of an Event
For example, the rectangle stores all the possible tosses of 2dice {(1,1), 1,2), (6,6)} Let A = tosses totaling 7 {(1,6),
(2, 5), (3,4), (4,3), (5,2), (6,1)}
P(Total = 7) + P(Total not equal to 7) = 1
A Ac
8/3/2019 BM6043_Probability
11/50
Can you provide examples ofcomplement probability?
Complement of an Event
8/3/2019 BM6043_Probability
12/50
6.12
Intersection of Two Events
The intersection of events A and B is the set of all samplepoints that are in both A and B.
The intersection is denoted: A and B
Thejoint probability of
A and B is the probability of
the intersection of A and B,i.e. P(A and B)
or P(AB)
A B
8/3/2019 BM6043_Probability
13/50
6.13
Intersection of Two Events
For example, let A = tosses where first toss is 1 {(1,1), (1,2),(1,3), (1,4), (1,5), (1,6)}
and B = tosses where the second toss is 5 {(1,5), (2,5), (3,5),
(4,5), (5,5), (6,5)}
The intersection is {(1,5)} must occur in both A and B
Thejoint probability of
A and B is the probability of
the intersection of A and B,
i.e. P(A and B) = 1/36
A B
8/3/2019 BM6043_Probability
14/50
Intersection of Two Events
Can you provide examples of jointprobability?
8/3/2019 BM6043_Probability
15/50
6.15
Union of Two Events
The union of two events A and B, is the event containing allsample points that are in A or B or both:
Union Probability of A and B is denoted: A or B
or P(AuB)
A B
8/3/2019 BM6043_Probability
16/50
6.16
Union of Two Events
For example, let A = tosses where first toss is 1 {(1,1), (1,2), (1,3),(1,4), (1,5), (1,6)}
and B is the tosses that the second toss is 5 {(1,5), (2,5), (3,5), (4,5),
(5,5), (6,5)}
Union of A and B is {(1,1), (1,2), (1,3), (1,4), (1,5), (1,6), (2,5), (3,5),
(4,5), (5,5), (6,5)}
A B
8/3/2019 BM6043_Probability
17/50
6.17
Mutually Exclusive Events
When two events aremutually exclusive (that is the twoevents cannot occur together), their joint probability is 0,
hence:
A B
Mutually exclusive; no points in common
Gender of employees: A = Male and B = Female
Manufactured part: A = Okay and B = Defective
f
8/3/2019 BM6043_Probability
18/50
6.18
Basic Relationships of Probability
Complement of Event
Intersection of Events
Union of Events
Mutually Exclusive Events
A Ac A B
A BA B
E l 1
8/3/2019 BM6043_Probability
19/50
6.19
Example 1
Why are some mutual fund managers more successful thanothers? One possible factor is where the manager earned his
or her MBA. The following table compares mutual fund
performance against the ranking of the university where thefund manager earned their MBA:
Mutual fund outperformsthe market
Mutual fund doesntoutperform the market
Top 20 MBA program .11 .29
Not top 20 MBA program .06 .54
E.g. This is the probability that a mutual fundoutperformsAND the manager was in a top-
20 MBA program; its a joint probability. Probability Matrix
E l 1
8/3/2019 BM6043_Probability
20/50
6.20
Example 1
Alternatively, we could introduce shorthand notation torepresent the events:
A1 = Fund manager graduated from a top-20 MBA program
A2 = Fund manager did not graduate from a top-20 MBA programB1 = Fund outperforms the market
B2 = Fund does not outperform the market
B1 B2
A1 .11 .29
A2
.06 .54
E.g. P(A2 and B1) = .06
= the probability a fund outperforms the market
and the manager isnt from a top-20 school.
0.40
0.60
0.17 0.83 1.00
M i l P b biliti
8/3/2019 BM6043_Probability
21/50
6.21
Marginal Probabilities
Marginal probabilities are computed by adding across rowsand down columns; that is they are calculated in themargins
of the table:
B1 B2 P(Ai)
A1 .11 .29 .40
A2 .06 .54 .60
P(Bj) .17 .83 1.00
P(B1) = .11 + .06
P(A2) = .06 + .54
whats the probability a fundoutperforms the market?
whats the probability a fund
manager isnt from a top school?
BOTH margins must add to 1
(useful error check)
C diti l P b bilit
8/3/2019 BM6043_Probability
22/50
6.
Conditional Probability
Conditional probability is used to determine how two eventsare related; that is, we can determine the probability of one
eventgiven the occurrence of another related event.
Conditional probabilities are written as P(A | B) and read as
the probability of A given B and is calculated as:
B A
How is this differ from
joint probability? Look at the denominator
C diti l P b bilit
8/3/2019 BM6043_Probability
23/50
6.23
Conditional Probability
Again, the probability of an eventgiven that another eventhas occurred is called a conditional probability
Note how A given B and B given A are related
Example: Conditional Probability
8/3/2019 BM6043_Probability
24/50
6.24
Example: Conditional Probability
You want to determine what changes in office design wouldimprove productivity. 70% of respondents believed noise
reduction would improve productivity and 67% said
increased office space would improve productivity. Inaddition, 56% respondents believed both would improve
productivity.
A worker is picked randomly and this worker believes noise
reduction would improve productivity. What is the
probability that this worker also believe increased officespace would improve productivity?
Conditional Probability
8/3/2019 BM6043_Probability
25/50
6.25
Conditional Probability
We want to calculate P(B1 | A1)
Thus, there is a 27.5% chance that that a fund will outperform the market
given that the manager graduated from a top-20 MBA program.
B1 B2 P(Ai)
A1 .11 .29 .40
A2 .06 .54 .60
P(Bj) .17 .83 1.00
Independence
8/3/2019 BM6043_Probability
26/50
6.26
Independence
One of the objectives of calculating conditional probability isto determine whether two events are related.
In particular, we would like to know whether they areindependent, that is, if the probability of one event isnot
affectedby the occurrence of the other event.
Two events A and B are said to be independent if
P(A|B) = P(A)
or
P(B|A) = P(B)
Independence
8/3/2019 BM6043_Probability
27/50
6.27
Independence
For example, we saw that
P(B1 | A1) = .275
The marginal probability for B1 is: P(B1) = 0.17
Since P(B1|A1) P(B1), B1 and A1 arenot independentevents.
Stated another way, they aredependent. That is, theprobability of one event (B1) is affectedby the occurrence of
the other event (A1).
Union
8/3/2019 BM6043_Probability
28/50
6.28
Union
We stated earlier that the union of two events is denoted as:A or B. We can use this concept to answer questions like:
Determine the probability that a fund outperforms the market
or the manager graduated from a top-20 MBA program.
Union
8/3/2019 BM6043_Probability
29/50
6.29
Union
Determine the probability that a fund outperforms (B1
)
or the manager graduated from a top-20 MBA program (A1).
B1 B2 P(Ai)
A1 .11 .29 .40
A2 .06 .54 .60
P(Bj) .17 .83 1.00
A1 or B1 occurs whenever:
A1 and B1 occurs, A1 and B2 occurs, orA2 and B1 occurs
P(A1 or B1) = .11 + .06 + .29 = .46
Union
8/3/2019 BM6043_Probability
30/50
6.30
Union
Determine the probability that a fund outperforms (B1
)
or the manager graduated from a top-20 MBA program (A1).
B1 B2 P(Ai)
A1 .11 .29 .40
A2 .06 .54 .60
P(Bj) .17 .83 1.00
P(A1 or B1) = .11 + .06 + .29 = .46
B1
A1
Alternatively
8/3/2019 BM6043_Probability
31/50
6.31
B1 B2 P(Ai)
A1 .11 .29 .40
A2 .06 .54 .60
P(Bj) .17 .83 1.00
B1
A1
Alternatively
Take 100% and subtract off when doesnt A1 or B1 occur?
i.e. at A2 and B2
P(A1
or B1
) = 1 P(A2
and B2
) = 1 .54 = .46
Probability Rules and Trees
8/3/2019 BM6043_Probability
32/50
6.32
Probability Rules and Trees
We introduce three rules that enable us to calculate theprobability of more complex events from the probability of
simpler events
The Complement Rule,
The Multiplication Rule, and
The Addition Rule
Complement Rule
8/3/2019 BM6043_Probability
33/50
6.33
Complement Rule
As we saw earlier with the complement event, thecomplement rule gives us the probability of an event NOT
occurring. That is:
P(AC) = 1 P(A)
For example, in the simple roll of a die, the probability of the
number 1 being rolled is 1/6. The probability that some
number other than 1 will be rolled is 1 1/6 = 5/6.
Multiplication Rule
8/3/2019 BM6043_Probability
34/50
6.34
Multiplication Rule
Themultiplication rule is used to calculate thejointprobability of two events. It is based on the formula for
conditional probability defined earlier:
If we multiply both sides of the equation by P(B) we have:
P(A and B) = P(A | B)P(B)
Likewise, P(A and B) = P(B | A) P(A)
If A and B are independent events, then P(A and B) = P(A)P(B)
Example of Multiplication I
8/3/2019 BM6043_Probability
35/50
6.35
Example of Multiplication I
A graduate statistics course has seven male and three femalestudents. The professor wants to select two students at
random to help her conduct a research project. What is the
probability that the two students chosen are female?
Let A represent the event that the first student is female
P(A) = 3/10 = .30
What about the second student?
Example of Multiplication I
8/3/2019 BM6043_Probability
36/50
6.36
Example of Multiplication I
A graduate statistics course has seven male and three femalestudents. The professor wants to select two students atrandom to help her conduct a research project. What is the
probability that the two students chosen are female?
Let B represent the event that the second student is female
P(B | A) = 2/9 = .22
That is, the probability of choosing a female studentgiventhat the first student chosen is 2 (females) / 9 (remainingstudents) = 2/9
Example of Multiplication I
8/3/2019 BM6043_Probability
37/50
6.37
Example of Multiplication I
A graduate statistics course has seven male and three femalestudents. The professor wants to select two students atrandom to help her conduct a research project. What is theprobability that the two students chosen are female?
Thus, we want to answer the question: what is P(A and B) ?
P(A and B) = P(A)P(B|A) = (3/10)(2/9) = 6/90 = .067
There is a 6.7% chance that the professor will choose twofemale students from her grad class of 10.
Example of Multiplication II
8/3/2019 BM6043_Probability
38/50
6.38
Example of Multiplication II
Refer to Example 6.5. The professor who teaches the courseis suffering from the flu and will be unavailable for twoclasses. The professors replacement will teach the next twoclasses. His style is to select one student at random and pickon him or her to answer questions during that class. What isthe probability that the two students chosen are female?
Let A represent the event that the first student is female
P(A) = 3/10 = .30
What about the second student?
Example of Multiplication II
8/3/2019 BM6043_Probability
39/50
6.39
p p
Let B represent the event that the second student is female
P(B | A) = 3/10 = .30
That is, the probability of choosing a female studentgiven
that the first student chosen is unchanged since the studentselected in the first class can be chosen in the second class.
P(A and B) = P(A)P(B|A) = (3/10)(3/10) = 9/100 = .090
What is the different
between
Multiplication
Example I and II?
Addition Rule
8/3/2019 BM6043_Probability
40/50
6.40
Recall: theaddition rule is used to compute the probabilityof event Aor Borboth A and B occurring; i.e. the union of
A and B.
P(A or B) = P(A) + P(B) P(A and B)
A B A B= +
P(A or B) = P(A) + P(B) P(A and B)If A and B are
mutually exclusive,
then this term
goes to zero
Example of Addition
8/3/2019 BM6043_Probability
41/50
6.41
p
In a large city, two newspapers are published, the Sun andthe Post. The circulation departments report that 22% of the
citys households have a subscription to the Sun and 35%
subscribe to the Post. A survey reveals that 6% of allhouseholds subscribe to both newspapers. What proportion
of the citys households subscribe to either newspaper?
That is, what is the probability of selecting a household at
random that subscribes to the Sun or the Post or both?
i.e. what is P(Sun or Post) ?
Example of Addition
8/3/2019 BM6043_Probability
42/50
6.42
p
In a large city, two newspapers are published, the Sun andthe Post. The circulation departments report that 22% of thecitys households have a subscription to the Sun and 35%subscribe to the Post. A survey reveals that 6% of allhouseholds subscribe to both newspapers. What proportionof the citys households subscribe to either newspaper?
P(Sun or Post) = P(Sun) + P(Post) P(Sun and Post)
= .22 + .35.06 = .51
There is a 51% probability that a randomly selectedhousehold subscribes to one or the other or both papers
Probability Trees
8/3/2019 BM6043_Probability
43/50
6.43
y
An effective and simpler method of applying the probabilityrules is the probability tree, wherein the events in an
experiment are represented by lines. The resulting figure
resembles a tree, hence the name. We will illustrate theprobability tree with several examples, including two that we
addressed using the probability rules alone.
Probability Trees
8/3/2019 BM6043_Probability
44/50
6.44
First selection Second selection
P(F)=3/10
P(M)=7/10 P
(F|M)=3/9
P(F|F)=2/9
P(M|M)=6/9
P(M|F)=7/9
This is P(F), the probability ofselecting a female student first
This is P(F|F), the probability ofselecting a female studentsecond, given that a female wasalready chosen first
Probability Trees
8/3/2019 BM6043_Probability
45/50
6.45
At the ends of the branches, we calculatejointprobabilities as the product of the individual probabilities
on the preceding branches.
First selection Second selection
P(F)=3/10
P(M)=7/10 P
(F|M)=3/9
P(F|F)=2/9
P(M|M)=6/9
P(M|F)=7/9
P(FF)=(3/10)(2/9)
P(FM)=(3/10)(7/9)
P(MF)=(7/10)(3/9)
P(MM)=(7/10)(6/9)
Joint probabilities
Example of Probability Trees
8/3/2019 BM6043_Probability
46/50
6.46
Suppose we have our grad class of 10 students again, butmake the student sampling independent, that is with
replacement a student could be picked first and picked
again in the second round. Our tree and joint probabilitiesnow look like: FF
MF
MM
FMP(F)
=3/10
P(M)=7/10 P(F|M)=3/10
P(F|F)=3/
10
P(M|M)=7/10
P(M|F)=7/10
P(FF)=(3/10)(3/10)
P(FM)=(3/10)(7/10)
P(MF)=(7/10)(3/10)
P(MM)=(7/10)(7/10)
Probability Trees
8/3/2019 BM6043_Probability
47/50
6.47
3/9 + 6/9= 9/9 = 1
2/9 + 7/9
= 9/9 = 1
3/10 + 7/10
= 10/10 = 1
The probabilities associated with any set of branches fromone node must add up to 1.00
First selection Second selection
P(F)=3/10
P(M)=7/10
P(F|M)=3/9
P(F|F)=2/9
P(M|M)=6/9
P(M|F)=7/9
Handy way to check
your work !
Probability Trees
8/3/2019 BM6043_Probability
48/50
6.48
Note: there is no requirement that the branches splits bebinary, nor that the tree only goes two levels deep, or that
there be the same number of splits at each sub node
Probability Trees
8/3/2019 BM6043_Probability
49/50
6.49
Law school grads must pass a bar exam. Suppose pass ratefor first-time test takers is 72%. They can re-write if they fail
and 88% pass their second attempt. What is the probability
that a randomly grad passes the bar?P(Pass) = .72
P(Fail and Pass)=
(.28)(.88)=.2464
P(Fail and Fail) =
(.28)(.12) = .0336
First exam
P(Pass)=
.72
P(Fail)=.28
Second exam
P(Pass|Fail)=.88
P(Fail|Fail)=.12
Probability Trees
8/3/2019 BM6043_Probability
50/50
6.50
What is the probability that a randomly grad passes the bar?There is almost a 97% chance they will pass the bar
P(Pass) = P(Pass 1st) + P(Fail 1st and Pass 2nd) =
= 0.7200 + 0.2464 = .9664P(Pass) = .72
P(Fail and Pass)=
(.28)(.88)=.2464
P(Fail and Fail) =
(.28)(.12) = .0336
First exam
P(Pass)=
.72
P(Fail)=.28
Second exam
P(Pass|Fail)=.88
P(Fail|Fail)=.12