• No results found

swm02_11.ppt

N/A
N/A
Protected

Academic year: 2020

Share "swm02_11.ppt"

Copied!
30
0
0

Loading.... (view fulltext now)

Full text

(1)
(2)

Chapter 11

(3)

Why Be Random?

 What is it about chance outcomes being random

that makes random selection seem fair? Two things:

 Nobody can guess the outcome before it

happens.

 When we want things to be fair, usually some

underlying set of outcomes will be equally likely (although in many games some

(4)

Why Be Random? (cont.)

 Example:

 Pick “heads” or “tails.”

 Flip a fair coin. Does the outcome match your

(5)

Why Be Random? (cont.)

 Statisticians don’t think of randomness as the

annoying tendency of things to be unpredictable or haphazard.

 Statisticians use randomness as a tool.

 But, truly random values are surprisingly hard to

(6)

Pick a Number

(7)

What Number did you pick?

 If selected randomly

 ______ select 1  ______ select 2  ______ select 3  ______ select 4

 Class picks

(8)
(9)

It’s Not Easy Being Random (cont.)

 It’s surprisingly difficult to generate random values even

when they’re equally likely.

 Computers have become a popular way to generate

random numbers.

 Even though they often do much better than humans,

computers can’t generate truly random numbers either.

 Since computers follow programs, the “random”

numbers we get from computers are really pseudorandom.

 Fortunately, pseudorandom values are good enough

(10)

It’s Not Easy Being Random (cont.)

 There are ways to generate random numbers so

that they are both equally likely and truly random.

 The best ways we know to generate data that

give a fair and accurate picture of the world rely on randomness, and the ways in which we draw conclusions from those data depend on the

(11)

What is Randomness?

 Random events

 Outcome unknown before event

 _______________________  _______________________

 No Structure in Short Term

 _______________________

 Structure in Long Term

(12)

How do we get random numbers?

 Computers?

 Pseudorandom numbers

 Random events

 Radioactive decay

 Random movements of molecules

 Table in Appendix E

 List of numbers 0 through 9.

(13)

A Simulation

 A simulation consists of a collection of things that

happen at random.

 The most basic event is called a component of

the simulation.

 Each component has a set of possible

(14)

A Simulation (cont.)

 The sequence of events we want to investigate is

called a trial.

 Trials usually involve several components.

 After the trial, we record what happened—our

response variable.

(15)

Simulation Steps

1. Identify the component to be repeated.

2. Explain how you will model the outcome.

3. Explain how you will simulate the trial.

4. State clearly what the response variable is.

5. Run several trials.

6. Analyze the response variable.

7. State your conclusion (in the context of the

(16)

Cereal Boxes: Using random numbers

Suppose a cereal manufacturer puts pictures of famous athletes in boxes of cereal to in the hopes of boosting sales. They announce that 30% of

the boxes will contain a picture of Tiger Woods, 30 % a picture of Lance Armstrong, and the rest a picture of Serena Williams. You want all three

(17)

Cereal Boxes cont.

 Simulation

 0,1,2: box has Tiger Woods

 3,4,5: box has Lance Armstrong

 6,7,8,9: box has Serena Williams

 Look at random numbers

(18)

Using random numbers

 Trial 1: 96299071969864 ________ boxes  Trial 2: 22063 ________ boxes

 Trial 3: 923 ________ boxes  Trial 4: 185 ________ boxes  Trial 5: 562 ________ boxes  Trial 6: 826992914 ________ boxes  Trial 7: 12538 ________ boxes

 Trial 8: 87294 ________ boxes

(19)

Using random numbers

 Out of 10 trials

- mean = ________ boxes

 More trials = more accurate result.

 Out of 200 trials

(20)

Example: Dice Rolling

 How many times do we need to roll a die before

we get a 6?

 Simulation

 1,2,3,4,5,6: Roll on die

 0,7,8,9: Throw out

 Look at random numbers

(21)

Using random numbers

 Throw out 0,7,8,9

3142436322346515553332 3552264432416524533316

 Trial 1: 3142436 _7_ rolls

 Trial 2: 322346 ___ rolls

 Trial 3: 515553332355226 ___ rolls

 Trial 4: 4432416 ___ rolls

(22)

Using random numbers

 Out of 5 trials

- mean number of rolls = ____

 More trials = more accurate result.

 Out of 200 trials

(23)

Example: Dorm Lottery

 40 people live on a dorm floor; 10 are on soccer

team. A lottery was drawn to select 3 people to live in triple suite. All 3 people selected were on soccer team. Is this fair?

 Simulation

 00,01,02,03,04,05,06,07,08,09: Soccer team

 10,11,12,…,39: Non-soccer team

(24)

Using Random Numbers

 Look at random numbers

47119 76651 21732 32364 58545 50277 57558 30390 18771 72703 11232 99884 05087 76839 65142 19994 91397 29350 83852 04905

 By twos

(25)

Using Random Numbers

 Throw out 40,41,…,99

11 21 23 23 02 03 18 17 27 03 11 23 29 05 08 39 14 21 39 20 05

(26)

Using Random Numbers

 Out of 7 trials

- no groups selected had all three people from soccer team.

 More trials = more accurate result.

 Out of 200 trials,

- only _______ groups selected had all three people from soccer team.

(27)

Your New Favorite Word!!

suggests

When you write a conclusion about your

simulation, you must state that the results

(28)

What Can Go Wrong?

 Don’t overstate your case.

 Always be sure to indicate that future results

will not match your simulated results exactly.

 Model the outcome chances accurately.

(29)

What have we learned?

 We will harness the power of randomness.

 A simulation model can help us investigate a

question for which:

 many outcomes are possible,

 we can’t (or don’t want to) collect data, and

 a mathematical answer is hard to calculate.

 We base our simulations on random values.

 Like all models, simulations can provide us with

(30)

Quick Practice

You have procured an 8 sided die….

1. How many times would you expect to roll the die

in order to get a number twice in a row?

2. What is the probability that you will get one even

and one odd number in two rolls?

3. How many “8’s” would you expect to get in 10

References

Related documents

There are ways to convert a LLL result into an explicit construction, but usually you need a lower dependency value. We won’t cover this (see Sections 6.8, 6.10 of

Drawing on history, politics, language, literature, contemporary media, music, art, and relationship building with Pacific communities, Pacific Studies and Samoan Studies

innovation in payment systems, in particular the infrastructure used to operate payment systems, in the interests of service-users 3.. to ensure that payment systems

F6150 Internal Options Ethernet or USB Communication Logic Inputs Voltage & Current Relay F6ControlPanel Communications Relay Sources Logic Outputs (Optional) under Test..

The Board’s Staff Consultation Paper on Auditing Estimates and Fair Value Measurements, issued in 2014, heightens the significance of this Consultation Paper as the usage

The main findings of Chapter 2 are that a larger cohort size reduces the wages of workers with medium and high degrees of occupational specialization, while employment effects

Product Name Technical Licences Technical Licenses Required/ Optional GIS 8.0 Required GIS_INTERACTIONSERVICE 8.0 Required ics_custom_media_channel 8.0

Es- tas nuevas estructuras nos permitir´ an reali- zar procesos como agregaci´ on de informaci´ on, asignaci´ on autom´ atica de clases sem´ anticas o desambiguaci´ on de