chapter 3: probability statistics. mcclave: statistics, 11th ed. chapter 3: probability 2 where...

47
Chapter 3: Probability Statistics

Upload: roberta-sparks

Post on 24-Dec-2015

252 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

Chapter 3: Probability

Statistics

Page 2: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

2

Where We’ve Been

Making Inferences about a Population Based on a Sample

Graphical and Numerical Descriptive Measures for Qualitative and Quantitative Data

Page 3: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

3

Where We’re Going

Probability as a Measure of Uncertainty

Basic Rules for Finding Probabilities Probability as a Measure of Reliability

for an Inference

Page 4: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

4

3.1: Events, Sample Spaces and Probability

An experiment is an act or process of observation that leads to a single outcome that cannot be predicted with certainty.

Page 5: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

5

3.1: Events, Sample Spaces and Probability

A sample point is the most basic outcome of an experiment.

A four

A Head

An Ace

Page 6: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

6

3.1: Events, Sample Spaces and Probability

A sample space of an experiment is the collection of all sample points. Roll a single die:

S: {1, 2, 3, 4, 5, 6}

Page 7: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

7

3.1: Events, Sample Spaces and Probability

Sample points and sample spaces are often represented with Venn diagrams.

Page 8: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

8

3.1: Events, Sample Spaces and Probability

All probabilities must be between 0 and 1.

The probabilities of all the sample points must sum to 1.

Probability Rules for Sample Points

1

1i

n

i

p

0 1ip

Page 9: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

9

3.1: Events, Sample Spaces and Probability

All probabilities must be between 0 and 1

The probabilities of all the sample points must sum to 1

Probability Rules for Sample Points

1

1i

n

i

p

0 1ip

0 indicates an impossible outcome and 1 a certain outcome.

Something has to happen.

Page 10: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

10

3.1: Events, Sample Spaces and Probability

An event is a specific collection of sample points: Event A: Observe an even number.

Page 11: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

11

3.1: Events, Sample Spaces and Probability The probability of an event is the sum of the

probabilities of the sample points in the sample space for the event. Event A: Observe an even number. P(A) = 1/6 + 1/6 + 1/6 = 3/6 = 1/2

Page 12: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

12

3.1: Events, Sample Spaces and Probability

Calculating Probabilities for Events Define the experiment. List the sample points. Assign probabilities to sample points. Collect all sample points in the event of

interest. The sum of the sample point probabilities is

the event probability.

Page 13: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

13

3.1: Events, Sample Spaces and Probability

Calculating Probabilities for Events Define the experiment List the sample points Assign probabilities to sample points Collect all sample points in the event of

interest The sum of the sample point probabilities is

the event probability

If the number of sample points gets too large, we need a way to keep track of how they can be combined for different events.

Page 14: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

14

3.1: Events, Sample Spaces and Probability

If a sample of n elements is drawn from a set of N elements (N ≥ n), the number of different samples is

!

.! )!

N N

n n N n

Page 15: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

15

3.1: Events, Sample Spaces and Probability

If a sample of 5 elements is drawn from a set of 20 elements, the number of different samples is

20 20! 20 19 18 3 2 1

15,504.5 5! 20 5)! 5 4 3 2 1 15 14 13 3 2 1

Page 16: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

16

3.2: Unions and Intersections

Compound EventsMade of two or

more other events

UnionA B

Either A or B, or both, occur

IntersectionA B

Both A and Boccur

Page 17: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

17

3.2: Unions and Intersections

Page 18: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

18

3.2: Unions and Intersections

A B

B C

A

B C

A C

A B C

Page 19: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

19

3.3: Complementary Events

The complement of any event A is the event that A does not occur, AC.

A: {Toss an even number}AC: {Toss an odd number}

B: {Toss a number ≤ 3}BC: {Toss a number ≥ 4}

A B = {1,2,3,4,6}[A B]C = {5}(Neither A nor B occur)

Page 20: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

20

3.3: Complementary Events

)(1)(

)(1)(

1)()(

APAP

APAP

APAP

C

C

C

Page 21: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

21

3.3: Complementary EventsA: {At least one head on two coin flips}

AC: {No heads}

43

41

41

43

41

41

41

1)(1)(

)(

)(

}{:

},,{:

C

C

C

APAP

AP

AP

TTA

THHTHHA

Page 22: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

22

3.4: The Additive Rule and Mutually Exclusive Events

The probability of the union of events A and B is the sum of the probabilities of A and B minus the probability of the intersection of A and B:

)()()()( BAPBPAPBAP

Page 23: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

23

3.4: The Additive Rule and Mutually Exclusive Events

P(Surgery or Obstetrics) ( )

( ) ( ) ( ) ( )

( ) .12 .16 .02 .26

P A B

P A B P A P B P A B

P A B

At a particular hospital, the probability of a patient having surgery (Event A) is .12, of an obstetric treatment (Event B) .16, and of both .02.

What is the probability that a patient will have either treatment?

Page 24: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

24

3.4: The Additive Rule and Mutually Exclusive Events

Events A and B are mutually exclusive if A B contains no sample points.

Page 25: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

25

3.4: The Additive Rule and Mutually Exclusive Events

)()()( BPAPBAP

If A and B are mutually exclusive,

Page 26: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

Additional information or other events occurring may have an impact on the probability of an event.

26McClave: Statistics, 11th ed. Chapter 3: Probability

Page 27: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

Additional information may have an impact on the probability of an event. P(Rolling a 6) is one-sixth

(unconditionally). If we know an even number was

rolled, the probability of a 6 goes up to one-third.

27McClave: Statistics, 11th ed. Chapter 3: Probability

Page 28: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

The sample space is reduced to only the conditioning event.

To find P(A), once we know B has occurred (i.e., given B), we ignore BC (including the A region within BC).

28McClave: Statistics, 11th ed. Chapter 3: Probability

B BC

A A

Page 29: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

29McClave: Statistics, 11th ed. Chapter 3: Probability

B BC

A A

)(

)()(

BP

BAPBAP

Page 30: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

30McClave: Statistics, 11th ed. Chapter 3: Probability

B

A

)(

)()(

BP

BAPBAP

Page 31: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

55% of sampled executives had cheated at golf (event A). P(A) = .55

20% of sampled executives had cheated at golf and lied in business (event B). P(A B) = .20

What is the probability that an executive had lied in business, given s/he had cheated in golf, P(B|A)?

31McClave: Statistics, 11th ed. Chapter 3: Probability

Page 32: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.5: Conditional Probability

P(A) = .55

P(A B) = .20 What is P(B|A)? )(

)()(

AP

ABPABP

364.55.

20.)( ABP

32McClave: Statistics, 11th ed. Chapter 3: Probability

Page 33: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.6: The Multiplicative Rule and Independent Events

The conditional probability formula can be rearranged into the Multiplicative Rule of Probability to find joint probability.

)(

)()(

BP

BAPBAP

)()()(

)()()(

ABPAPBAP

or

BAPBPBAP

33McClave: Statistics, 11th ed. Chapter 3: Probability

Page 34: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.6: The Multiplicative Rule and Independent Events

Assume three of ten workers give illegal deductions Event A: {First worker selected gives an illegal deduction} Event B: {Second worker selected gives an illegal

deduction} P(A) = P(B) = .1 + .1 + .1 = .3

P(B|A) has only nine sample points, and two targeted workers, since we selected one of the targeted workers in the first round: P(B|A) = 1/9 + 1/9 = .11 + .11 = .22

The probability that both of the first two workers selected will have given illegal deductions P(AB) = P(B|A)P(A) = .(3) (.22) = .066

34McClave: Statistics, 11th ed. Chapter 3: Probability

Page 35: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

McClave: Statistics, 11th ed. Chapter 3: Probability

35

3.6: The Multiplicative Rule and Independent Events

Page 36: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.6: The Multiplicative Rule and Independent Events

A Tree Diagram

First selected worker

Second selected worker

36McClave: Statistics, 11th ed. Chapter 3: Probability

Page 37: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.6: The Multiplicative Rule and Independent Events

Dependent Events P(A|B) ≠ P(A) P(B|A) ≠ P(B)

Independent Events P(A|B) = P(A) P(B|A) = P(B)

Studying stats 40 hours per week

Working 40 hours per week

Having blue eyes

37McClave: Statistics, 11th ed. Chapter 3: Probability

Page 38: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.6: The Multiplicative Rule and Independent Events

Dependent Events P(A|B) ≠ P(A) P(B|A) ≠ P(B)

Independent Events P(A|B) = P(A) P(B|A) = P(B)

Mutually exclusive events are dependent: P(B|A) = 0

Since P(B|A) = P(B),

P(AB) = P(A)P(B|A) = P(A)P(B)

38McClave: Statistics, 11th ed. Chapter 3: Probability

Page 39: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.7: Random Sampling

If n elements are selected from a population in such a way that every set of n elements in the population has an equal probability of being selected, the n elements are said to be a (simple) random sample.

39McClave: Statistics, 11th ed. Chapter 3: Probability

Page 40: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.7: Random Sampling

How many five-card poker hands can be dealt from a standard 52-card deck?

Use the combination rule:

960,598,2)!552(!5

!52

5

52

n

N

40McClave: Statistics, 11th ed. Chapter 3: Probability

Page 41: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.7: Random Sampling

Random samples can be generated by Mixing up the elements and drawing by hand,

say, out of a hat (for small populations) Random number generators Random number tables

Table I, App. B Random sample/number commands on

software

41McClave: Statistics, 11th ed. Chapter 3: Probability

Page 42: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Some Additional Counting Rules

Situation

Multiplicative Rule Draw one element from each

of k sets, sized n1, n2, n3, … nk

Permutations Rule Draw n elements, arranged

in a distinct order, from a set of N elements

Partitions Rule Partition N elements into k

groups, sized n1, n2, n3, … nk (ni=N)

Number of Different Results

McClave: Statistics, 11th ed. Chapter 3: Probability

42

!!!!

!

)!(

!

321

321

k

Nn

k

nnnn

N

nN

NP

nnnn

Page 43: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Some Additional Counting Rules

Multiplicative RuleAssume one professor from each of the six departments in a division will be selected for a special committee. The various departments have four, seven, six, eight, six and five professors eligible. How many different committees, X*, could be formed?

McClave: Statistics, 11th ed. Chapter 3: Probability

43

360,87

568674

* 321

knnnnX

Page 44: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Some Additional Counting Rules

Permutations If there are eight horses entered in a race, how many different win, place and show possibilities are there?

McClave: Statistics, 11th ed. Chapter 3: Probability

44

336)!38(

!8

)!(

!

nN

NPNn

Page 45: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Some Additional Counting Rules Partitions Rule

The technical director of a theatre has twenty stagehands. She needs eight electricians, ten carpenters and two props people. How many different allocations of stagehands, Y*, can there be?

McClave: Statistics, 11th ed. Chapter 3: Probability

45

1 2 3

! 20!* 8,314,020

! ! ! ! 8!10!2!k

NY

n n n n

Page 46: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Bayes’s Rule

Given k mutually exclusive and exhaustive events B1, B2,… Bk, and an observed event A, then

)

1 1 2 2

( | ) ( ) / ( )

( ) ( |.

( ) ( | ) ( ) ( | ) ( ) ( | )

i i

i i

k k

P B A P B A P A

P B P A B

P B P A B P B P A B P B P A B

46McClave: Statistics, 11th ed. Chapter 3: Probability

Page 47: Chapter 3: Probability Statistics. McClave: Statistics, 11th ed. Chapter 3: Probability 2 Where We’ve Been Making Inferences about a Population Based

3.8: Bayes’s Rule

Suppose the events B1, B2, and B3, are mutually exclusive and complementary events with P(B1) = .2, P(B2) = .15 and P(B3) = .65. Another event A has these conditional probabilities: P(A|B1) = .4, P(A|B2) = .25 and P(A|B3) = .6.

What is P(B1|A)?

158.5075.

08.

39.0375.08.

08.

6.65.25.15.4.2.

4.2.

)|()()|()()|()(

)|()(

)(/)()|(

332211

11

11

BAPBPBAPBPBAPBP

BAPBP

APABPABP

47McClave: Statistics, 11th ed. Chapter 3: Probability