probability

profileovermorrow888
P1-IntroProbability.pdf

LSP 121

P1 - Introduction to Probability

Probability Outline • Concepts/Vocabulary • Sample space and sample space size • Calculating Probability • Types of Probability

– theoretical – empirical

• Theoretical vs. Empirical probability • Other useful probability calculations • Gambler's Fallacy • Expected Value • Type I/Type II error

2

Probability

• How likely is it that something will happen ?

3

Expressing Probability

Event

• Something that occurs

• For example: roll of dice, flip of coin, weather forecast, election

5

Outcome

• Result of an event

• Has a value of interest to us

• For example: value on rolled die is 6, heads, rain, Bob Smith is elected treasurer

6

Sample Space

• List of all possible outcomes of an event or multiple events

7

Sample Space =

All Possible Outcomes

8

Sample Space = All Possible Outcomes

• Single event

• Examples Flip one coin

sample space = Tail ,Head

Roll one die sample space = 1,2,3,4,5,6

9

Sample Space = All Possible Outcomes

• Multiple events

• Example - Flip two coins

Sample space all combinations Head,Head Head,Tail Tail,Head Tail,Tail

10

Sample Space Size

Number of (Count of ) possible outcomes in the sample space for a single event

Or

Number of (Count of) all possible combinations in the sample space for multiple events

11

Sample Space Size

Sample Space Size =

Number of Possible Outcomes =

Number of Possible Combinations

12

Sample Space Size for Single Event

• number of the possible outcomes – count them

• Examples Flip one coin

sample space size = 2

Roll one die sample space size = 6

13

Sample Space Size for Multiple Events

multiply the sample space size of each of the events

for example: Sample space size for throwing two dice =

sample space size for one die x

sample space size for second die

14

Sample Space Size = Number of Possible Outcomes for multiple events

M = number of possible outcomes for event A N = number of possible outcomes for event B O = number of possible outcomes for event C

Total number of possible outcomes (size of sample space ) for events A and B and C (the three events happen together)

M x N x O

15

Sample Space Size for Two Dice

Sample space size for throwing two dice = sample space size for one die = 6

x sample space size for second die = 6

= ?

In this case, we can visualize all outcomes….

16

Possible Combinations/Sample Space and Values when throwing Two Dice

Die 1

D ie

2

Value Die 1

V a lu

e D

ie 2

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

Combined value of both dice 17

Calculating Sample Space Size – Example #1

• A restaurant menu offers – two choices for an appetizer, – five choices for a main course, and

– three choices for a dessert.

How many different possible three-course meals are there?

18

Calculate Sample Space Size – Example #1

• A restaurant menu offers two choices for an appetizer, five choices for a main course, and three choices for a dessert.

How many different possible three-course meals are there?

2 x 5 x 3 = 30

19

Calculating Sample Space Size – Example #2

• During one quarter, a college offers – 3 natural science classes, – 4 social science classes, – 10 English classes, and

– 2 fine arts classes.

How many possible four-class combinations are there ?

20

Calculating Sample Space Size – Example #2

• During one quarter, a college offers – 3 natural science classes, – 4 social science classes, – 10 English classes, and

– 2 fine arts classes.

How many possible four-class combinations are there ?

3 x 4 x 10 x 2 = 240

21

To calculate Number of Possible Combinations

(Sample Space Size)

1. Draw a diagram of the components 2. Note the number of values for each

component 3. Multiply the numbers of values together

The result is the number of possible combinations.

22

Example – Number of Possible Combinations

A bank allows you to select an identification code that is five places long.

There are limits for the values that can be in each of the five places:

1. the first place must be an upper-case or lower-case letter in the English alphabet

2. the second place must be a lower-case letter in the English alphabet

3. the third place must be a number 0-9 4. the fourth place must be an upper-case letter in the English

alphabet or a lower-case letter in the English alphabet or a number 0-9

5. the fifth place must be Y or N How many possible 5-place combinations are there ?

23

Number of combinations – approach (cont.)

• write the places in the code as a series of X's

X X X X X

• write the number of possible values below each X

X X X X X 26+26 26 10 26+26+10 2

24

Number of combinations – approach (cont.)

• Calculate the number of possible values below each X

X X X X X 26+26 26 10 26+26+10 2

52 26 10 62 2

25

Number of combinations – approach (cont.)

• Multiply the numbers of possible values together

52 x 26 x 10 x 62 x 2

Number of possible combinations = 1,676,480

26

Among other uses….

• Number of possible combinations (sample space size) can be used in calculating probabilities

27

In general

Probability of an Outcome Occurring

P(A) = proportion of the event(s) in which a particular outcome (A) occurs

28

Calculating Probability

For an event:

Probability =

number of outcomes of a particular value ______________________________________________________________________

number of possible outcomes (all possible combinations)

29

Calculating Probability of an Outcome Occurring

• For example, – Rolling a die (event) has 6 possible outcomes,

(1,2,3,4,5,6).

– Each one of those possible outcomes can occur one way

– Probability of any of those outcomes (e.g. rolling a 3) is 1/6

30

Expressing Probability

• As a proportion 0.0 � 1.0

• As a percentage 0 � 100 %

• As a fraction e.g. ¼

• As a number of outcomes e.g. 1 in 6

31

Types of Probability

Basic Types of Probability

• Theoretical, or a priori

• Empirical

33

Theoretical or a Priori

• Theoretical, or a priori probability –

– Can be calculated before event

34

Empirical Probability

– based on the results of observations or experiments.

35

Theoretical Probability

Calculated before an event occurs

36

Calculating Probability

Theoretical Probability =

number of ways an outcome can occur ______________________________________________________________________

number of possible outcomes (sample space size)

37

Theoretical Probability – calculated before an event

• P(A) = (number of ways A can occur) _______________________________________________________________

(total number of outcomes (sample space size))

e.g. #1 Probability of a head landing in a coin toss

#2 Probability of rolling a 5 with one die

#3 Probability that your phone number ends with 9

38

Theoretical Probability Example #1

Theoretical Probability of a head landing in a coin toss

number of ways "heads" can occur = 1

sample space size (heads, tails) = 2

theoretical probability of landing heads in a coin toss =

½ or .5 or 50 % or 1 of 2

39

Theoretical Probability Example #2

Theoretical Probability of rolling a "5" with one die

number of ways "5" can occur = 1

sample space size (1,2,3,4,5,6) = 6

theoretical probability of rolling a "5" with one die =

1/6 or .1667 or 16.67 % or 1 of 6

40

Theoretical Probability Example #3

Theoretical Probability your phone number ends with "9"

number of ways "9" can occur = 1

sample space size (0,1,2,3,4,5,6,7,8,9) = 10

theoretical probability your phone number ends with "9" =

1/10 or .10 or 10.0 % or 1 of 10

41

Calculating Theoretical Probabilities "Either/Or"

• What is the theoretical probability of either "this" outcome happening or "that" outcome happening ?

• Assume that the outcomes don’t overlap

42

Calculating Theoretical Probabilities "Either/Or"

• What is the theoretical probability of either "this" outcome happening or "that" outcome happening ?

Add the theoretical probabilities of each P(A or B) = P(A) + P(B)

43

Calculating Theoretical Probabilities "Either/Or"

Example: You roll a single die.

What is the probability of rolling either a 2 or a 3?

44

Calculating Theoretical Probabilities "Either/Or"

Example: You roll a single die. What is the probability of rolling either a 2 or a 3?

P(2 or 3) = P(2) + P(3) =

1/6 + 1/6 = 2/6 = 1/3

45

Calculating Theoretical Probabilities - Multiple Independent Events

"And" • Event A and Event B and Event C, etc. all

occur

• Assume all events are independent – the outcome of one does not affect the

outcome of the other

46

Calculating Theoretical Probabilities - Multiple Independent Events

"And"

• The probability of all events occurring, multiply the probabilities

P(A and B and C), = P(A) x P(B) x P(C)

47

Calculating Theoretical Probabilities Multiple Independent Events

"And"

Example #1: What is the theoretical probability that both your phone number and mine end in "8" ?

48

Calculating Theoretical Probabilities Multiple Independent Events

"And"

Example #1: What is the theoretical probability that both your phone number and mine end in "8" ?

Theoretical Probability that your phone number ends in "8" = .1 or 1/10

Theoretical Probability that my phone number ends in "8" = .1 or 1/10

49

Calculating Theoretical Probabilities Multiple Independent Events

"And"

Example #1: What is the theoretical probability that both your phone number and mine end in "8" ?

Theoretical Probability that your phone number ends in "8" =.1

Theoretical Probability that my phone number ends in "8" = .1

Theoretical Probability that both of our phone numbers end in "8" =

.1 x .1 = .01 or 1/10 x 1/10 = 1/100

50

Calculating Theoretical Probabilities Multiple Independent Events

"And" Example #2

• You toss three coins. What is the theoretical probability of getting three tails?

That is…. Coin Toss Result for Coin A = Tails

and

Coin Toss Result for Coin B = Tails and

Coin Toss Result for Coin C = Tails

51

Calculating Theoretical Probabilities Multiple Independent Events

“And” • Example #2 • You toss three coins.

– What is the theoretical probability of getting three tails?

1/2 x 1/2 x 1/2 = 1/8

Coin A Coin B Coin C

52

Calculating Theoretical Probabilities - Multiple Independent Events

“And”

Example #3

• Find the theoretical probability that a 100-year flood will strike a city in two consecutive years

(FEMA definition of a 100-year flood is that it occurs in 1% of the years in question.)

53

Calculating Theoretical Probabilities - Multiple Independent Events

“And”

Example #3

• Find the theoretical probability that a 100-year flood will strike a city in two consecutive years

(1 in 100) x (1 in 100) = Year 1 Year 2

54

Calculating Theoretical Probabilities - Multiple Independent Events

“And” Example #3

• Find the theoretical probability that a 100-year flood will strike a city in two consecutive years

(1 in 100) x (1 in 100) = 1/10000

(1 in 100) x (1 in 100) = 0.01 x 0.01 = 0.0001

Year 1 Year 2

55

Empirical Probability

– Calculated based on the results of observations or experiments.

56

Empirical Probability – calculated after events occur

• Empirical P(A) =

(number of A outcomes) _______________________________________________________________

(total number of observations)

57

Empirical Probability – calculated after events

Example #1

– Weatherperson Fred has predicted the weather 1000 times

– Weatherperson Fred has predicted the weather correctly 250 times

58

Empirical Probability – calculated after events

Example #1

– Weatherperson Fred has predicted the weather 1000 times

– Weatherperson Fred has predicted the weather correctly 250 times

– The empirical probability of Weatherperson Fred predicting the weather correctly is 250/1000 = 1/4

59

Empirical Probability Example #2

• Records indicate that the Funky River has crested above flood level just four times in the past 2000 years.

– What is the empirical probability that the Funky River will crest above flood level in any given year? (measurement is whether a flood has occurred in a particular year, yes or no)

60

Empirical Probability Example #1

• Records indicate that the Funky River has crested above flood level just four times in the past 2000 years.

– What is the empirical probability that the Funky River will crest above flood level in any given year?

4/2000 = 1/500 = 0.002

61

Comparing Theoretical and Empirical Probabilities

• Theoretical probability of a coin flip resulting in heads = .5

• The empirical probability (your actual results) when flipping a coin may not be the same

62

Are theoretical and empirical probabilities equal for an

outcome ?

63

Create a probability matrix to display and compare the theoretical and empirical

probabilities

64

Probability Matrix

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

65

Compare Theoretical and Empirical Probability Example

• Flip two coins 15 times. – What is the theoretical probability of each

outcome ?

– What is the empirical probability of each outcome ?

66

What is the sample space for two coins?

Tossing 2 coins has 4 possible outcomes – Sample space is HT,HH,TH,TT

Enter all the possible outcomes in the left hand column (outcomes) of the probability matrix

67

Update Probability Matrix with all possible outcomes

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH

HT

TH

TT

Total 1.0 1.0 68

What is the sample space size for flipping two coins?

Sample space size for tossing 2 coins is 4

(sample space size for coin A) x (sample space size for coin B )

2 x 2 = 4

There should be 4 outcomes in the Outcomes column.

69

Calculate Theoretical Probability

• Theoretical probability =

ways outcome can occur = 1 sample space size = 4

in this case theoretical probability for each outcome is ¼

70

Add Theoretical Probability to the matrix

• Theoretical probability =

ways outcome can occur = 1 sample space size = 4

Total theoretical probability should equal 1.

71

Add Theoretical Probabilties

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH 1/4

HT 1/4

TH 1/4

TT 1/4

Total 4/4 = 1 72

Calculate Empirical Probabilities

• Empirical probability =

count of each actual outcome total number of events/observations

empirical probability for each outcome depends on the actual results

73

For this example

• Count for each actual outcome

HH = 2 HT = 5 TH = 4 TT = 4

• Add number of times each outcome actually occurs to the matrix

74

Add number of occurrences

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH 1/4 2

HT 1/4 5

TH 1/4 4

TT 1/4 4

Total 1 15 75

Total of actual occurrences should equal number of trials

• Count for each actual outcome

HH = 2 HT = 5 TH = 4 TT = 4

Total = 15 • Add the total number of occurrences to the

matrix – double check 76

Add the total of occurrences Double check that it matches the number of trials

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH 1/4 2

HT 1/4 5

TH 1/4 4

TT 1/4 4

Total 1 15 77

Calculate Empirical Probabilities

• Empirical probability = count for each actual outcome

15 Empirical probability of HH = 2/15 Empirical probability of HT = 5/15 Empirical probability of TH = 4/15 Empirical probability of TT = 4/15

78

Total of Empirical Probabilities

• Should be equal to 1

Empirical probability of HH = 2/15 Empirical probability of HT = 5/15 Empirical probability of TH = 4/15 Empirical probability of TT = 4/15

Total = 15/15 = 1 79

Add Empirical Probabilties to the matrix

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH 1/4 2 2/15

HT 1/4 5 5/15

TH 1/4 4 4/15

TT 1/4 4 4/15

Total 1 15 15/15 = 1 80

Probability Matrix Complete

Outcomes

(Sample Space)

Theoretical Probability

Number of times this combination appears in this experiment

Empirical Probability

HH 1/4 2 2/15

HT 1/4 5 5/15

TH 1/4 4 4/15

TT 1/4 4 4/15

Total 1 15 1 81

Theoretical = Empirical Probability

Compare Probabilities for Each Combination

In this case….

Will theoretical and empirical probability ever be equal ?

• The Law of Large Numbers says that – as you repeat the event (millions of times), – the empirical probability (actual results) will

approach the theoretical probability.

83

Law of Large Numbers

• http://bcs.whfreeman.com/ips4e/cat_010/a pplets/expectedvalue.html

84

Thought Question #1:

What would the sample space size be

if we were flipping three coins ?

85

Thought Question #2:

What would the sample space be

if we were flipping three coins ?

86

Thought Question #3:

What would the theoretical probabilities be

if we were flipping three coins ?

87

Other Useful Probability Calculations

88

Probability of an Event Not Occurring

• P(not A) = 1 - P(A)

• For example, – If the probability of rolling a 3 with one die is

1/6, – then the probability of NOT rolling a 3 with

one die is • 1- 1/6 = 5/6

89

Probability of At Least Once

90

Probability of At Least Once

• What is the probability of an outcome happening at least once in a number of trials?

• P(at least one outcome A in n trials) =

1 - [P(not A in one trial)]n

91

Probability of At Least Once Example #1

• What is the probability that a region will experience at least one 100-year flood during the next 15 years?

92

Probability of At Least Once Example #1

• What is the probability that a region will experience at least one 100-year flood during the next 15 years?

• Probability of a flood in any one year = 1/100 = .01 • Probability of no flood in any one year = 99/100 = .99 • The number of trials = 15

• P(at least one 100-year flood in 15 years) = 1 – (0.99)15 = 1 - 0.860058 = 0.139942

Stated as percentage = 13.9942% 93

Probability of At Least Once Example #2

• You purchase 10 lottery tickets, for which the theoretical probability of winning some prize on a single ticket is 1 in 10 (or .1).

• What is the theoretical probability that you will have at least one winning ticket?

94

Probability of At Least Once Example #2

• You purchase 10 lottery tickets, for which the probability of winning some prize on a single ticket is 1 in 10 (or .1).

• What is the probability that you will have at least one winning ticket?

• Probability of winning with any one ticket = .1 • Probability of not winning with any one ticket = .9 • Number of trials = 10

P(at least one winner in 10 tickets) = 1 – (0.9)10 = 1 - 0.348678 = 0.651322

Stated as percentage to three decimal places= 65.132%

95

Calculating Power of

• Excel has a function called Power

Calculating Power of a number with Excel

96

The "at least once" approach

• use this approach only when the problem uses the phrase "at least once" or "at least one"

97

Probability of Exactly Once

98

Probability of an Event Happening Exactly Once

• What is the probability of an outcome happening exactly once in a number of trials ?

( P(yes) * [ P(no)] number of trials-1) * number of trials

99

Probability of an Event Happening Exactly Once

• What is the probability of an outcome happening exactly once in a number of trials ?

• For example: – If the probability of an outcome is 0.3 in one trial, what

is the probability of an outcome occurring exactly once in four trials ?

P(exactly one yes in 4 trials) = [P(yes) * P(no) * P(no) * P(no) ] * 4

100

Probability of an Event Happening Exactly Once

If the probability of an outcome is 0.3 in one trial, what is the probability of an outcome occurring exactly once in four trials ?

Here are the four possible combinations: [P(yes) * P(no) * P(no) * P(no)] [P(no) * P(yes) * P(no) * P(no)] [P(no) * P(no) * P(yes) * P(no)] [P(no) * P(no) * P(no) * P(yes)]

101

Probability of an Event Happening Exactly Once

If the probability of an outcome is 0.3 in one trial, what is the probability of an outcome occurring exactly once in four trials ? Here are the four possible combinations:

A. [P(.3) * P(.7) * P(.7) * P(.7)] = 0.1029 B. [P(.7) * P(.3) * P(.7) * P(.7)] = 0.1029 C. [P(.7) * P(.7) * P(.3) * P(.7)] = 0.1029 D. [P(.7) * P(.7) * P(.7) * P(.3)] = 0.1029

This is an Either/Or case…A or B or C or D 102

Probability of an Event Happening Exactly Once

If the probability of an outcome is 0.3 in one trial, what is the probability of an outcome occurring exactly once in four trials ?

Here are the four possible outcomes: A. [P(.3) * P(.7) * P(.7) * P(.7)] B. [P(.7) * P(.3) * P(.7) * P(.7)] C. [P(.7) * P(.7) * P(.3) * P(.7)] D. [P(.7) * P(.7) * P(.7) * P(.3)]

103

Probability of an Event Happening Exactly Once

This is an “Either/Or” case…A or B or C or D could occur So the probability of A or B or C or D =

P(A) + P(B) + P(C) + P(D)

Here are the four possible outcomes with probabilities: A. [P(.3) * P(.7) * P(.7) * P(.7)] = 0.1029 B. [P(.7) * P(.3) * P(.7) * P(.7)] = 0.1029 C. [P(.7) * P(.7) * P(.3) * P(.7)] = 0.1029 D. [P(.7) * P(.7) * P(.7) * P(.3)] = 0.1029

P(A or B or C or D) = .4116 104

Probability of an Event Happening Exactly Once

If the probability of an outcome is 0.3 in one trial, what is the probability of an outcome occurring exactly once in four trials ?

In this example, the Number of Trials = 4

In this example, probability of exactly one is [0.3 * 0.7 * 0.7 * 0.7] * 4 = 0.1029 * 4

= 41.16 % as a percent with two decimal places

105

Probability of an Event Happening Exactly Once

106

• What is the probability that a region will experience exactly one 100-year flood during the next 25 years?

• Probability of a flood in any one year = 1/100 = .01 • Probability of no flood in any one year = 99/100 = .99 • The number of trials = 25

( P(yes) * [ P(no)] number of trials-1) * number of trials

• P(exactly one 100-year flood in 25 years) = .01 * (0.99)25-1 = .01 * 0.785678 * 25

= 0.19642 Percentage to three decimal places =19.642%

Calculation of Probability Gambler’s Fallacy

• You are playing craps in Vegas. – You have had a string of losses. – You figure since your luck has been so bad, it has to

balance out and turn good Bad assumption!

• This is an example of Gambler’s Fallacy – specifically the "just world" hypothesis

– Each event is independent of another and has nothing to do with the previous run. Especially in the short run

107

Gambler's Fallacy - example

• The probability of winning at any one spin at roulette is 0.473

• What is the probability of winning at roulette six spins in a row ?

0.473 * 0.473 * 0.473 * 0.473 * 0.473 * 0.473

(0.473)6 = 0.1119868

108

What are the probabilities for the next spin ?

• after six winning spins

– probability of winning on the next spin is 0.473

– probability of losing on the next spin is 1.0 – 0.473 = 0.527

• the prior winning spins have no impact on the probabilities of this single spin

109

Expected Value

Expected Value

• Uses – probabilities of possible outcomes – and the dollar values of the possible

outcomes

to estimate values that can be compared and used to make decisions about whether a course of action is advantageous

111

Expected Value

• A practical (rational)way to determine the dollar value of outcomes and compare them

Calculated by

Dollar value of the outcome of an event multiplied by

the probability that the outcome will occur

112

Expected value Example #1

Example: I receive a raffle ticket for my birthday. The raffle prize is $1000. The probability that I will win is 1/10000.

The expected value to me is

+$1000 *1/10000 = $1000/10000 = +$.10

113

Expected value Example #1 continued

Fred offers to buy my raffle ticket for $1.

The expected value of that transaction to me is

+$1 x 1.00 = +$1.00

114

Should I sell the raffle ticket to Fred ?

compare expected value of keeping ticket with expected value of selling ticket

Keep ticket (expected value of raffle ticket to me � +$.10)

Sell ticket (expected value of what Fred will pay me for it � +$1.00)

Choose the outcome with the higher expected value

115

Calculating Expected Value

• What if there are multiple related events? – What is the expected value from the set of

events?

• Expected value = event 1 value x event 1 probability

+ event 2 value x event 2 probability + …

116

A tip

• Make sure you keep signs for each dollar value straight

• Money coming to you (or your organization) = +

• Money going from you (or your organization) = -

117

Expected Value

• Two points of view: – Value to the “buyer”

• money has come out of your pocket (-)

– Value to the “seller” • money is going into your pocket (+)

118

Expected Value Buyer - Example #1

Raffle ticket example:

What is the expected value of a raffle ticket ?

A. The ticket costs $5.00 B. The raffle prize is $10,000. The probability that a given ticket will win is 1/10000.

Expected value A. - $5.00 x 1.00 = - $5.00 B. + $10,000 x 1/10000 = +$1.00 Expected value = ( - $5.00 )

+( +1.00 ) - $4.00

Money out of your pocket To buy the ticket, you must pay,

so probability is 100% or 1.0

119

On the average, you would lose $4.00 per ticket purchased. You should not buy this ticket

Expected Value Buyer - Example #2

• Suppose that a $1 lottery ticket has the following probabilities: – 1 in 5 win a free $1 ticket; – 1 in 100 win $5; – 1 in 100,000 to win $1000; – 1 in 10 million to win $1 million.

– What is the expected value of this lottery ticket?

– Should you buy this ticket ? 120

Expected Value Buyer - Example #2

• Ticket purchase: value -$1, prob 1.0 • Win free ticket: value $1, prob 1/5 • Win $5: value $5, prob 1/100 • Win $1000: prob 1/100,000 • Win $1million: prob 1/10,000,000

-$1 x 1= -1; $+1 x 1/5 = +$0.20; $+5 x 1/100 = +$0.05; $+1000 x 1/100,000 = +$0.01; $+1,000,000 x 1/10,000,000 = +$0.10

121

Expected Value Buyer - Example #2

• Now sum all the products: -$1 x 1 = -1.00 +$1 x 1/5 = +0.20 +$5 x 1/100 = +0.05 +$1000 x 1/100,000 = +0.01 +$1,000,000 x 1/10,000,000 = +0.10

total -$0.64

Thus, averaged over many tickets, you should expect to lose $0.64 for each lottery ticket that you buy.

122

Expected Value Buyer - Example #2

Thus, averaged over many tickets, you should expect to lose $0.64 for each lottery ticket that you buy.

Should you buy this ticket ? • The expected value for this lottery ticket is less than zero

(negative value -$.64) so you should not buy this ticket.

• If the expected value were greater than zero (positive), you should buy the ticket.

123

Expected Value – Seller Example

• Suppose an insurance company (Company A) sells policies for $1000 each.

• The company knows that 10% of its policy holders will submit a successful claim that averages $2500 each.

• The company knows that an additional 10% of its policy holders will submit a successful claim that averages $5000 each.

• How much can the company expect to make per customer?

• If the company sold 100 policies, how much would it expect to gain/lose ?

124

Expected Value – Seller Example

• Company A takes in (+) $1000 100% of the time (when a policy is sold)

• Company A pays out (-) $2500 10% of the time

• Company A pays out (-) $5000 10% of the time

125

Expected Value – Seller Example

+ $1000 x 1.0 = + $1000 - $2500 x 0.1 = - $ 250 - $5000 x 0.1 = - $ 500

total = +$250

• Company A would expect to make $250 from each customer

• If Company A sells 100 policies, it expects to make $25,000 126