Math Olympiad 2011 Northwest Missouri State University Neil Hatfield How Statistics Won World War II.

Slides:



Advertisements
Similar presentations
The German Tank Problem
Advertisements

High School Graduation Test Review Domain: Data Analysis How is data presented, compared and used to predict future outcomes?
The German Tank Problem
1 Chapter 15 System Errors Revisited Ali Erol 10/19/2005.
What Is a Sampling Distribution?
Copyright © 2007 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 19 Confidence Intervals for Proportions.
Stat 321 – Day 24 Point Estimation (cont.). Lab 6 comments Parameter  Population Sample Probability Statistics A statistic is an unbiased estimator for.
Information from Samples Alliance Class January 17, 2012 Math Alliance Project.
“There are three types of lies: Lies, Damn Lies and Statistics” - Mark Twain.
Reasoning and Sense Making with Data Analysis T ANKS, P LANES, AND UNICEF Math Olympiad 2011 Northwest Missouri State University Neil Hatfield.
1 Psych 5500/6500 Statistics and Parameters Fall, 2008.
Hypothesis Testing and T-Tests. Hypothesis Tests Related to Differences Copyright © 2009 Pearson Education, Inc. Chapter Tests of Differences One.
Chapter 7 Sampling Distributions
Chapter 7: Sampling Distributions
+ The Practice of Statistics, 4 th edition – For AP* STARNES, YATES, MOORE Chapter 7: Sampling Distributions Section 7.1 What is a Sampling Distribution?
Ch 8 Estimating with Confidence. Today’s Objectives ✓ I can interpret a confidence level. ✓ I can interpret a confidence interval in context. ✓ I can.
Chapter 4 Statistics. 4.1 – What is Statistics? Definition Data are observed values of random variables. The field of statistics is a collection.
Ch 8 Estimating with Confidence. Today’s Objectives ✓ I can interpret a confidence level. ✓ I can interpret a confidence interval in context. ✓ I can.
Sampling Distributions Chapter 7. The German Tank Problem In WWII, the Allies captured several German Tanks. Each one had a serial number on it.
7.1: What is a Sampling Distribution?!?!. Section 7.1 What Is a Sampling Distribution? After this section, you should be able to… DISTINGUISH between.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 10 Comparing Two Populations or Groups 10.1.
Chapter 8 : Estimation.
Chapter 7 Sampling Distributions Target Goal: DISTINGUISH between a parameter and a statistic. DEFINE sampling distribution. DETERMINE whether a statistic.
Chapter 8: Confidence Intervals based on a Single Sample
Copyright © 2009 Pearson Education, Inc. Chapter 19 Confidence Intervals for Proportions.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 7 Sampling Distributions 7.1 What Is A Sampling.
CONFIDENCE INTERVALS: THE BASICS Unit 8 Lesson 1.
Intro to Inference & The Central Limit Theorem. Learning Objectives By the end of this lecture, you should be able to: – Describe what is meant by the.
A particular manufacturer produces AA batteries that are designed to last an average of 17 hours with a standard deviation of 0.8 hours. Quality control.
Sampling Distribution, Chp Know the difference between a parameter and a statistic.
Learning Objectives After this section, you should be able to: The Practice of Statistics, 5 th Edition1 DESCRIBE the shape, center, and spread of the.
STAT03 - Descriptive statistics (cont.) - variability 1 Descriptive statistics (cont.) - variability Lecturer: Smilen Dimitrov Applied statistics for testing.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 7 Sampling Distributions 7.1 What Is A Sampling.
Evaluating Hypotheses. Outline Empirically evaluating the accuracy of hypotheses is fundamental to machine learning – How well does this estimate its.
WHAT IS A SAMPLING DISTRIBUTION? Textbook Section 7.1.
The Practice of Statistics, 5th Edition Starnes, Tabor, Yates, Moore Bedford Freeman Worth Publishers CHAPTER 10 Comparing Two Populations or Groups 10.1.
+ The Practice of Statistics, 4 th edition – For AP* STARNES, YATES, MOORE Chapter 7: Sampling Distributions Section 7.1 What is a Sampling Distribution?
Statistical Decision Making. Almost all problems in statistics can be formulated as a problem of making a decision. That is given some data observed from.
Sampling Distributions
Confidence Intervals and Sample Size
Classifying Solutions to Systems of Equations
Chapter 7: Sampling Distributions
WARM -UP Through data compiled by the auto industry 12% of Americans are planning on buying a hybrid. A recent national poll randomly asked 500 adults.
Research methods Lesson 2.
CHAPTER 7 Sampling Distributions
Chapter 9: Sampling Distributions
CHAPTER 7 Sampling Distributions
Random Rectangles When given the cue turn the paper over. Within 5 seconds make a guess for the average area of the rectangles. When given the cue turn.
Chapter 7: Sampling Distributions
CHAPTER 7 Sampling Distributions
Chapter 7: Sampling Distributions
CHAPTER 7 Sampling Distributions
Confidence Intervals for Proportions
Test Drop Rules: If not:
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 9: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
CHAPTER 7 Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
The Practice of Statistics – For AP* STARNES, YATES, MOORE
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Chapter 7: Sampling Distributions
Samples and Populations
Presentation transcript:

Math Olympiad 2011 Northwest Missouri State University Neil Hatfield How Statistics Won World War II

The Problem In , US and British tanks were far superior than the German Panzer tanks. The Germans made revisions to the Panzers and introduced the much more powerful Mark V tanks. The Allied Forces were unsure how many Mark V tanks the Germans could produce, thus making it unclear whether or not any invasion of the European continent on the western front would succeed.

The Problem, cont. The Critical Question: “How many Mark V tanks are produced each month?” British and American Intelligence agencies worked separately and independently to try and answer this question. Best Estimate: 1,400 tanks produced per month British and American Statisticians also became intrigued by the problem and began working. Vital Information: Both groups and access to the Serial Numbers of captured Mark V tanks. The Serial Numbers were known to be sequential. Your Challenge: Choose a good estimator for the total number of tanks produced each month.

The Challenge You will each work in a team of fellow statisticians. Each team will need to decide on a possible method for estimating the number of tanks produced each month. Possible Methods: Take the sample mean and add three times the standard deviation. Double the sample mean. Double the sample median. The sky is your limit. Once your team has decided upon a method, you will then need to do some data collection. Each team will make use of one paper and one bag found on the tables.

The Challenge, cont. Each team needs to record their method on their paper. Each team will then randomly draw out five (5) cards from their paper bag WITHOUT LOOKING. Record these numbers on the packet and as well as the Mean and Standard Deviation Use your group’s method to calculate, the estimated total number of tanks produced each month. Repeat this process two more times. Find the mean of your three values and report that to me.

Values for

Which method (estimator) was best? What is meant by the word “best”? You can’t judge an estimator by how it performs on one random sample. We need to evaluate it over many random samples. We want our estimator to be unbiased. Unbiased: on average, the estimator hits the true value of what it is estimating. Biased: on average, the estimator misses the true value of what it is estimating. (Systematically misses.) We would like our estimator to have low variability. We would like the estimates produced over many random samples to be relatively close to one another.

Biased/Unbiased Estimators

High/Low Variance Estimators

What was actually used? The British and American statisticians ended using the following estimator. is the estimate for the total number of tanks produced that month. M is the maximum serial number sampled. n is the sample size. They estimated that 246 tanks were produced each month. After the war, German production records revealed that production was actually 245 tanks per month.

Let’s look at some graphs.

Does this end here? No! The process that we have used here can be used in other ways. The number of buzzers at a restaurant. The number of taxis in New York City. iPhones In 2008, an man in London asked people to post their iPhone serial number and the date of purchase. From this information, he was able to calculate that Apple had sold 9.1 million iPhones by the end of September. Generate another set of research questions similar to what we did here and propose a strategy to find a potential solution to each