Vous êtes sur la page 1sur 18

Module 1

Probability

Review of Sets

Definitions

Union of Sets (AUB): Elements in either set Intersection (AB): Elements in both sets Complement (Ac): Elements not in A A(BUC) = (AB)U(AC) AU(BC) = (AUB)(AUC) n(A) = n(AB) + n(ABc) n(AUB) = n(A) + n(B) n(AB) n(AUBUC) = n(A) + n(B) + n(C) n(AB) n(AC) n(BC) + n(ABC)

Rules

Solving Problems

Method

Draw diagram of intersecting sets Label known quantities Work from the inside out to determine unknowns N = 100, A = 40, B = 30, AB = 20 Find ABc = 40 20 = 20 Find (AUB)c = 100 (40 + 30 20) = 50

Example 1

Solving Problems

Example 2

A = 40, B = 30, C = 20 AB = 20, AC = 10, BC = 10 ABC = 5 ABCc = AB ABC = 20 5 = 15 ABcC = 10 5 = 5 AcBC = 10 5 = 5 ABcCc = A ABCc ABcC ABC = 15 AcBCc = 5 AcBcC = 5 AUBUC = (40 + 30 + 20) (20 + 10 + 10) + 5 = 55

Calculations

Using Table

Use table if Ac is as important as A


For instance, not just male, but male and female Or looking for values such as (AcBc) Draw table with rows representing one variable and columns representing another. Systematically calculate desired values using set rules: n(A) = N n(Ac) n(ABc) = n(A) n(AB)

Method

Example Problem

A survey of 1000 students:


500 students are male 600 plan to attend college 200 are immigrants 350 are males/college 150 are imm/college 100 are immigrant males 80 are male/immigrants/college How many students are male, non-immigrants, who do not plan to attend college?
Imm & College: Not Needed Male & College: 350 (Given) Male & No College 100 - 80 = 20 400 - 279 = 130

Males: 500 (Given)

Male & Imm: 100 (Given) M & Non-I: 500 - 100 = 400

80 (Given) 350 - 80 = 270

Probability Definitions

Sample Point: Simple outcome of experiment

Rolling a 4 on a die

Sample Space (S): All possible outcomes

Set for rolling a die: {1, 2, 3, 4, 5, 6}


Can not role a 3 and an even number at same time Even and odd rolls include all possible outcomes

Mutually Exclusive: Never at same time (AB)=0

Exhaustive: Include entire sample space

Probability Definitions (Same as Sets)

Event: Collection of sample points

Event A: Rolling an even number with die: {2, 4, 6}

Union (AUB): Outcomes in events A or B

A: {2, 4, 6}, B: {4, 5, 6}


A: {2, 4, 6}, B: {4, 5, 6} A: {2, 4, 6} Ac: {1, 3, 5}

AUB = {2, 4, 5, 6}
AB = {4, 6}

Intersection (AB): Outcomes in events A and B

Complement (Ac): Outcomes not in A

Probability Definition and Rules

Probability Definition
Probability Rules
P(Ac) = 1 P(A)

Law of Total Probability

Note: Ai are mutually exclusive and exhaustive

Other useful Rules

DeMorgans Laws

(AUB)c = AcBc (AB)c = AcUBc Example: Not (even or > 3) = odd and (<= 3) P(A) = P(AB) + P(ABc) P(AUB) = P(A) + P(B) P(AB) P(AUBUC) = P(A) + P(B) + P(C) P(AB) P(AB) P(AB) + P(ABC)

Relating unions and intersections (same as sets)


Example

A local survey indicated


80% own auto 60% own house 50% own both What percentage own an auto or a house, but not both? What percentage own neither an auto nor a house? P(ABc)+P(AcB) = (.80 .50) + (.60 .50) = .40 P(AcBc) = P[(AUB)c] = 1 (.8 + .6 .5) = .1

Solution

Conditional Probability

Definitions
Example Law of Total Probability

Sample Problem

A survey of company clients indicated


30% have life insurance 70% medical 20% both 50% of those with only life will renew policy 40% of those with only medical will renew 60% with both will renew Determine probability that a random policy holder will renew? Draw Venn diagram and calculate regions. Set up equation for conditional probability. Use conditional definition to change and probability to conditional.

Method

Solution
A = LMc B = LcM C = LM P[A] = P[L] P[LM] = .3 - .2 = .1 P[B] = P[M] P[LM] = .7 - .2 = .5 P[C] = P[LM] = .2

Note: Looking for conditional probability that person will renew (E), given that they hold a policy (AUBUC). A, B, and C are mutually exclusive, so equations simplify.

Bayes Theorem

Useful when swapping conditional probability

Example

Two urns have 5 red and 6 blue balls. A ball from urn 1 is picked randomly and placed in urn 2. If a red ball is pulled from urn 2, what is the probability that a red ball was picked from urn 1?

Solution

Calculate Probabilities

P[R1] = 5/11 P[R2|R1] = 6/12

P[B1] = 6/11 P[R2|B1] = 5/12

Use Bayes Theorem

Sample Problem
Given the following data, what is the probability of a person having an accident falling into the 26 30 bracket? Age of Driver Group 1: 18-20 Group 2: 21-25 Group 3: 26-30 Group 4: 31-65 Group 5: >65 Probability of Accident .07 .05 .03 .02 .05 Portion of Drivers .03 .05 .10 .52 .30

Independence

Events are independent if the probability of one is not affected by the other. Independence Equations

P[AB] = P[A] P[B] P[A|B] = P[A] P[A] = P[B] = A&B independent P[AUB] = P[A] + P[B] P[AB] = P[A]+ P[B] P[A]*P[B] P[AUB] = + - = 5/8

Example