You are on page 1of 36

ECON 225: Data and

Statistics for Economics


Lecture 8
Recap
• The probability model consists of: sample space, event space, and a
probability function that follows the 3 axioms of probability
• Disjoint events are events that can never happen together.
• Addition rule: P(A or B) = P(A) + P(B) if A and B disjoint
• Events are independent if the realization of one does not affect the
realization of the other
Plan for today
• The multiplication rule for independent events
• Problem solving using the addition and multiplication rules
• The general addition rule and the general multiplication rule
• Tree diagrams and Bayes’s rule
Multiplication rule for independent events
• Definition: Two events A and B are independent if knowing that one
occurs does not change the probability that the other occurs
• Multiplication rule for independent events: If A and B are
independent, P(A and B) = P(A)P(B)

Venn diagram:
Event A and event B. The intersection
represents the event {A and B} and
outcomes common to both A and B.
Example of multiplication rule
• Suppose a couple will have three children. What are the possible
arrangements of boys and girls?
• Sample space: {BBB, BBG, BGB, BGG, GBB, GBG, GGB, GGG}
• With all 8 outcomes equally likely, we can tell that the
probability of each occurring is 1/8
Example of multiplication rule
• Suppose a couple will have three children. What are the possible
arrangements of boys and girls?
• Sample space: {BBB, BBG, BGB, BGG, GBB, GBG, GGB, GGG}
• With all 8 outcomes equally likely, we can tell that the
probability of each occurring is 1/8
• Since each birth is independent of the previous, we can apply
the multiplication rule
• For any sequence of boys and girls, for example, for BBB:
• P(BBB) = P(B)*P(B)*P(B) = (1/2)*(1/2)*(1/2) = 1/8
• Same answer as when we listed all of the possible outcomes!
Example 1: Combining the rules
• Suppose we change the question of the experiment to: What are the
number of girls (X) the couple has?
• Now the sample space is S = {0,1,2,3}. What is the probability
function?
Example 1: Combining the rules
• Suppose we change the question of the experiment to: What are the
number of girls (X) the couple has?
• Now the sample space is S = {0,1,2,3}. What is the probability
function?
• We calculate the probabilities using both the multiplication rule and
the addition rule for disjoint events:
• P(X=0) = P(BBB) = 1/8
• P(X=1) = P(BBG or BGB or GBB) = P(BBG) + P(BGB) + P(GBB) by the
addition rule
• P(X=1) = P(B)P(B)P(G) + P(B)P(G)P(B) + P(G)P(B)P(B) by multiplication
rule
• P(X=1) = (1/2)(1/2)(1/2) + (1/2)(1/2)(1/2) + (1/2)(1/2)(1/2) = 3/8
The probability mass function
• Continuing the calculations, we obtain the probability mass function
for the number of girls X:

Note: disjoint events are never independent


Extensions of the multiplication rule
• If two events A and B are independent, then
• A and 𝐵! are independent
• 𝐴! and B are independent
• 𝐴! and 𝐵! are independent
• As we have seen already in the example, the
multiplication rule can be applied to more than two
events, provided they are all independent
Example of multiplication rule extension
• The EMIT drug test will occasionally produce a “false-positive” result,
indicating drug use when the individual has not used drugs. The
probability of a false-positive result for one person is 0.2%, or 0.002.
What is the probability that at least one false positive will occur if
150 individuals free of illegal drugs are tested with EMIT?

• 𝑃 𝑎𝑡 𝑙𝑒𝑎𝑠𝑡 𝑜𝑛𝑒 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒 = 1 − 𝑃 𝑛𝑜 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒𝑠 by complement rule


• = 1 − 𝑃 150 𝑛𝑒𝑔𝑎𝑡𝑖𝑣𝑒𝑠
• = 1 − 0.998!"# by multiplication rule
• = 1 − 0.741 = 0.259
Example of multiplication rule extension
• The EMIT drug test will occasionally produce a “false-positive” result,
indicating drug use when the individual has not used drugs. The
probability of a false-positive result for one person is 0.2%, or 0.002.
What is the probability that at least one false positive will occur if
150 individuals free of illegal drugs are tested with EMIT?
negative

• 𝑃 𝑎𝑡 𝑙𝑒𝑎𝑠𝑡 𝑜𝑛𝑒 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒 = 1 − 𝑃 𝑛𝑜 𝑝𝑜𝑠𝑖𝑡𝑖𝑣𝑒𝑠 by complement rule


• = 1 − 𝑃 150 𝑛𝑒𝑔𝑎𝑡𝑖𝑣𝑒𝑠
• = 1 − 0.998!"# by multiplication rule
• = 1 − 0.741 = 0.259
Example 2
• Suppose that a survey was conducted to determine the number of
glasses of soda consumed by American adults. Let X represent the
number of glasses consumed in a typical day. The probabilities for X
are as follows:

X 0 1 2 3 4+

Probability 0.52 0.28 0.09 0.04 0.07

Let A = number of glasses of soda is 1 or more. What is P(A)?


P(X>= 1) = 1 - P (0) = 1 - 0.52 = 0.48
Example 3
Consider a probability model consisting of randomly drawing 2 balls
(without replacement) from a jar containing 2 red and 3 blue balls. Let
A represent the event that exactly 1 out of the 2 balls is blue. What is
P(A)?
2R, 3B
P(Blue and Red) = P(B) . P(A)
A = {BR, RB}
= 3/5 . 2/4
P (A) = P (BR) + P (RB)
= (3/5) (2/4) + (2/5) (3/4)
= 15/20
= 3/5 = 3/5
Example 4
Suppose that the events A and B are disjoint. Event A occurs with
probability 0.3. What can we say for sure about P(A or B)?

a) P(A or B) < 0.3. OR = +


b) P (A or B) > 0.3.
c) P (A or B) < 0.7.
d) P (A or B) > 0.7.
Addition rules
• Definition: The union of any collection of events is the event
that at least one of the collection occurs
• The addition rules in probability relate to unions of events:
that event A or B occurs
• We have already discussed the addition rule for disjoint events.
This rule can apply to to any number of disjoint events:

P(A or B or C) = P(A) + P(B) + P(C)


General addition rule for probability
• General additional rule for any two
events A and B:
• The probability that A occurs, or B occurs,
or both events occur is:
• 𝑃(𝐴 𝑜𝑟 𝐵) = 𝑃(𝐴) + 𝑃(𝐵) – 𝑃(𝐴 𝑎𝑛𝑑 𝐵)
General addition rule for probability
• General additional rule for any two
events A and B:
• The probability that A occurs, or B occurs,
or both events occur is:
• 𝑃(𝐴 𝑜𝑟 𝐵) = 𝑃(𝐴) + 𝑃(𝐵) – 𝑃(𝐴 𝑎𝑛𝑑 𝐵)

Example: What is the probability of randomly drawing either an ace or a heart from a deck of
52 playing cards? There are 4 aces in the pack and 13 hearts. However, 1 card is both an ace
and a heart. Thus:
P(ace or heart) = P(ace) + P(heart) – P(ace and heart)
= 4/52 + 13/52 – 1/52 = 16/52 ≈ 0.31
Example 5: General addition rule
Deborah thinks she has probability 0.7 of being made partner of
her law firm and that Matthew has probability 0.5 of making
partner. She also believes there is probability 0.3 that they will
both be made partners. What is the probability of at least one of
them being made partner?
P (D) = 0.7
P (M) = 0.5
P (D and M) = 0.3

P (D or M) = P(D) + P(M) - P (D and M)


= 0.7 + 0.5 - 0.3
= 0.9
Example 5: General addition rule
Deborah thinks she has probability 0.7 of being made partner of
her law firm and that Matthew has probability 0.5 of making
partner. She also believes there is probability 0.3 that they will
both be made partners. What is the probability of at least one of
them being made partner?

P(at least one makes partner)


= P(Deborah) + P(Matt) – P(both)
= 0.7 + 0.5 – 0.3 = 0.9
3 types of probabilities: Joint
• Consider a standard deck of 52 playing cards:
• Event K: draw a King
• Event S: draw a Spade
• C: Clubs, H: Hearts, D: diamonds

• Definition: A joint probability is the probability that two


events both occur: P(A and B) or P(A & B) or P(A ∩ B)
• E.g. P(K and S) = 1/52
3 types of probabilities: Marginal

• Definition: A marginal probability is the probability of


a single event occurring. This is defined in contrast to
the joint probability.
• E.g. P(K) = 4/52 = 1/13
• The marginal probability can be calculated as a sum of
certain joint probabilities:
• P(K) = P(K and S) + P(K and H) + P(K and C) + P(K and D)
= 4/52
3 types of probabilities: Conditional
• Definition: A conditional probability is the probability of an
event given that another event has occurred. P(A given B has
occurred), P(A | B)
• P(K | S) = 1/13
• P(S | K) = ¼
• The conditional probability can be written as a ratio of the joint
and the marginal probabilities:

𝑃(𝐴 𝑎𝑛𝑑 𝐵)
𝑃 𝐴 𝐵) =
𝑃(𝐵)
Example of joint probability table from
Statistics Canada
Education and labour force status for 25-54 year olds

How do you interpret these numbers?


Joint probability table
For an unemployed person, what is the probability that they have a
university degree? What kind of probability is the answer?
Joint probability table
For an unemployed person, what is the probability that they have a
university degree? What kind of probability is the answer?

Imagine 10,000 people. 521 would be unemployed and 127 of the 521 would
Have University degrees. The more educated
P(Univ deg | Unemp) = 127/521 = 0.24 have higher chance of
P(Not HS grad | Unemp) = 82/521 = 0.16 unemployment?
How does the unemployment probability vary
by educational attainment?

P(Unemp. | Not HS grad.) = 0.0082/0.0988 = 0.083


Contradicts previous slide?
P(Unemp. | HS grad.) = 0.0104/0.1879 = 0.055
P(Unemp. | Some post-sec.) = 0.0028/0.0495 = 0.056
P(Unemp. | Post-sec. deg.) = 0.0180/0.3707 = 0.048
P(Unemp. | Univ. deg.) = 0.0127/0.2931 = 0.043
General multiplication rule
Multiplication rule: The probability that any two events, A
and B, happen together is:
𝑃(𝐴 𝑎𝑛𝑑 𝐵) = 𝑃(𝐴)𝑃(𝐵|𝐴)

P(B|A) is the conditional probability that B occurs, given the


information that A occurs.
Tree diagrams
• Conditional probabilities can get complex, and it is often a
good strategy to build a probability tree that represents all
possible outcomes graphically and assigns conditional
probabilities to subsets of events.
Tree diagram for chat room habits for
three adult age groups
Tree diagrams
• Conditional probabilities can get complex, and it is often a
good strategy to build a probability tree that represents all
possible outcomes graphically and assigns conditional
probabilities to subsets of events.
Tree diagram for chat room habits for
three adult age groups

P(chatting) = 0.136 + 0.099 + 0.017


= 0.252
About 25% of all adult Internet users
visit chat rooms.
Example: baseball
What is the probability of a high school athlete playing professional
baseball? 0.006392 + 0.001854 = 0.008246 = 0.8246%

0.068 X 0.094 = 0.006392

TOTAL PRPBABILITY : 1
0.068 X 0.906 = 0.061608
Proven !!

0.932 X 0.002 = 0,001864

0.932 X 0,998 = 0.930136


Example: baseball
What is the probability of a high school athlete playing professional
baseball?
P(Professional and College)
P(B and A) = P(A)P(B | A)
= (0.068)(0.094) = 0.006392

P(Professional and not College)


P(B and Ac) = P(A)P(B | Ac)
= (0.932)(0.002) = 0.001864

P(B) = 0.006392 + 0.001864 = 0.008256


The probability of a high school athlete
playing professional baseball is about
0.8%.
Bayes’s rule
An important application of conditional probabilities is Bayes’s rule.

• If a sample space is decomposed in k disjoint events, A1, A2, … , Ak,


none with a null probability but P(A1) + P(A2) + … + P(Ak) = 1,

• And if B is any other event such that P(B) is not 0 or 1, then:


Bayes’s rule in the baseball example
What proportion of professional baseball players competed in college?

0.068 X 0.094 = 0.006392

0.068 X 0.094 = 0.006392

0.932 X 0.002 = 0,001864

0.932 X 0,998 = 0.930136


Bayes’s rule in the baseball example
What proportion of professional baseball players competed in college?

About 77% of professional baseball


players competed in college.
For next class
• Reading: Alwan 4.3, 5.1-5.3
• For practice: 4.73, 5.9, 5.29, 5.31
• Practice midterm has been posted to Canvas
• Reminder to review the group project criteria

You might also like