Florida State University College of Law Research Center Statistics Concepts for Law Students Spring 2012 Workshop Jon R. Lutz

Slides:



Advertisements
Similar presentations
In 1999, Sally Clark was convicted of the murder of her two sons. The data: In 1996, her first son died apparently of cot death at a few weeks of age.
Advertisements

Beginning Probability
Lecture Discrete Probability. 5.2 Recap Sample space: space of all possible outcomes. Event: subset of of S. p(s) : probability of element s of.
AP STATISTICS Simulation “Statistics means never having to say you're certain.”
AP STATISTICS Simulating Experiments. Steps for simulation Simulation: The imitation of chance behavior, based on a model that accurately reflects the.
March 31, 2015Applied Discrete Mathematics Week 8: Advanced Counting 1 Discrete Probability Example I: A die is biased so that the number 3 appears twice.
Mathematics in Today's World
AP Biology Laws of Probability Probability & Genetics.
Unit 4 Sections 4-1 & & 4-2: Sample Spaces and Probability  Probability – the chance of an event occurring.  Probability event – a chance process.
More Probability STA 220 – Lecture #6 1. Basic Probability Definition Probability of an event – Calculated by dividing number of ways an event can occur.
Chapter 3 Probability.
Games of probability What are my chances?. Roll a single die (6 faces). –What is the probability of each number showing on top? Activity 1: Simple probability:
22C:19 Discrete Structures Discrete Probability Fall 2014 Sukumar Ghosh.
3.6: Probabilities Through Simulations Objective: To simulate probabilities using random number tables and random number generators CHS Statistics.
Statistics Introduction.
Section The Idea of Probability Statistics.
Section 6.2 ~ Basics of Probability Introduction to Probability and Statistics Ms. Young.
Probability Chapter 3. § 3.1 Basic Concepts of Probability.
CHAPTER 6 Random Variables
The Inexpert Witness Born 1933 Distinguished paediatrician Famous for “Munchausen Syndrome by Proxy” Expert witness in cases of suspected child abuse and.
5-2 Probability Distributions This section introduces the important concept of a probability distribution, which gives the probability for each value of.
Sets, Combinatorics, Probability, and Number Theory Mathematical Structures for Computer Science Chapter 3 Copyright © 2006 W.H. Freeman & Co.MSCS SlidesProbability.
Unit 5: Probability Sample Space.
Section 7.1: Chance and Probability. Probability Chance behavior is unpredictable in the short run (you probably can’t guess what number will be drawn,
Apr. 8 Stat 100. To do Read Chapter 21, try problems 1-6 Skim Chapter 22.
AP Statistics: Section 8.2 Geometric Probability.
Florida State University College of Law Research Center Statistics Concepts for Law Students Fall ‘08 Workshop Jon R. Lutz.
Copyright © 2014 Pearson Education, Inc. All rights reserved Chapter 5 Modeling Variation with Probability.
Section 6.3 Binomial Distributions. A Gaggle of Girls Let’s use simulation to find the probability that a couple who has three children has all girls.
Warm-Up 1. Expand (x 2 – 4) 7 1. Find the 8 th term of (2x + 3) 10.
Bernoulli Trials Two Possible Outcomes –Success, with probability p –Failure, with probability q = 1  p Trials are independent.
Introduction to Behavioral Statistics Probability, The Binomial Distribution and the Normal Curve.
+ The Practice of Statistics, 4 th edition – For AP* STARNES, YATES, MOORE Chapter 6: Random Variables Section 6.3 Day 1 Binomial and Geometric Random.
Probability Lecture 2. Probability Why did we spend last class talking about probability? How do we use this?
22C:19 Discrete Structures Discrete Probability Spring 2014 Sukumar Ghosh.
Copyright (C) 2002 Houghton Mifflin Company. All rights reserved. 1 Understandable Statistics Seventh Edition By Brase and Brase Prepared by: Mistah Flynn.
Mendel Carefully Accumulated Data And Realized That The Principles Of Probability Could Be Used To Explain The Results.
Probability Distributions: Binomial & Normal Ginger Holmes Rowell, PhD MSP Workshop June 2006.
Reasoning with Probs How does evidence lead to conclusions in situations of uncertainty? Bayes Theorem Data fusion, use of techniques that combine data.
Basic Concepts of Probability
Sally Clark. Sally Clark (August 1964 – 15 March 2007) was a British lawyer who became the victim of a miscarriage of justice when she was wrongly convicted.
Simulating Experiments Introduction to Random Variable.
Unit 4 Section 3.1.
Did Mendel fake is data? Do a quick internet search and can you find opinions that support or reject this point of view. Does it matter? Should it matter?
Section The Idea of Probability AP Statistics
Section 6.3 Day 1 Binomial Distributions. A Gaggle of Girls Let’s use simulation to find the probability that a couple who has three children has all.
HAWKES LEARNING Students Count. Success Matters. Copyright © 2015 by Hawkes Learning/Quant Systems, Inc. All rights reserved. Section 7.1 Introduction.
Lesson 10: Using Simulation to Estimate a Probability Simulation is a procedure that will allow you to answer questions about real problems by running.
AP STATISTICS LESSON THE IDEA OF PROBABILITY.
Probability and Sample Space…….
Chapter Five The Binomial Probability Distribution and Related Topics
Random Variables.
22C:19 Discrete Math Discrete Probability
Conditional Probability
CHAPTER 12: Introducing Probability
Probability and Counting Rules
Chapter 17 Thinking about Chance.
Statistics 1: Elementary Statistics
Dimension Three: Extending and Refining Knowledge
Lesson 10.1 Sample Spaces and Probability
Statistics 1: Elementary Statistics
Chapter 6: Random Variables
Chapter 6: Introduction to Genetics
Probability.
Multiplication Principle for Counting
Warm Up 1) A t-shirt company makes shirts in sizes S, M, L, XL and XXL and in the colors chartreuse, burgundy, fuchsia and mauve. How many different types.
Section 6.1 The Idea of Probability
6.2 Independence and the Multiplication Rule
I flip a coin two times. What is the sample space?
Probability Probability Principles of EngineeringTM
Presentation transcript:

Florida State University College of Law Research Center Statistics Concepts for Law Students Spring 2012 Workshop Jon R. Lutz

Florida State University College of Law Research Center Coin Flip Odds when you flip a coinOdds when you flip a coin 50/50 or ½ that it will be heads or tails50/50 or ½ that it will be heads or tails Each flip of the coin has the same oddsEach flip of the coin has the same odds IndependenceIndependence What are the odds of two heads in a rowWhat are the odds of two heads in a row Multiply the oddsMultiply the odds ½ x ½ = ¼½ x ½ = ¼

Florida State University College of Law Research Center Consider the two patterns HTH and HTT. Which of the following is true? The average number of tosses until head tail head is larger than the average number of tosses until head tail tailThe average number of tosses until head tail head is larger than the average number of tosses until head tail tail The average number of tosses until head tail head is the same as the average number of tosses until head tail tailThe average number of tosses until head tail head is the same as the average number of tosses until head tail tail The average number of tosses until head tail head is smaller than the average number of tosses until head tail tail.The average number of tosses until head tail head is smaller than the average number of tosses until head tail tail.

Florida State University College of Law Research Center Formula To get the answer, look at the n "end" subsequences (X_n), (X_{n-1}, X_n), (X_{n-2}, X_{n-1}, X_n),..., (X_{n-k}, X_{n-k+1},..., X_n),...(X_1,..., X_n), and compare them to the n "begin" subsequences (X_1), (X_1, X_2), (X_1,X_2,X_3),..., (X_1,..., X_k),..., (X_1,..., X_n). Count up the k's between 1 and n such that the "end" subsequence of length k is the same as the "begin" subsequence of length k, and sum up 2^k over all such k to get the expected number of tosses you're looking for. Let's look at the two examples discussed: HTH and HTT. For HTH, we have that H = H, TH != HT, HTH = HTH, so we get 2 + 2^3 = 10. For HTT, we have that T != H, TT != HT, HTT = HTT, so we get 2^3 = 8.To get the answer, look at the n "end" subsequences (X_n), (X_{n-1}, X_n), (X_{n-2}, X_{n-1}, X_n),..., (X_{n-k}, X_{n-k+1},..., X_n),...(X_1,..., X_n), and compare them to the n "begin" subsequences (X_1), (X_1, X_2), (X_1,X_2,X_3),..., (X_1,..., X_k),..., (X_1,..., X_n). Count up the k's between 1 and n such that the "end" subsequence of length k is the same as the "begin" subsequence of length k, and sum up 2^k over all such k to get the expected number of tosses you're looking for. Let's look at the two examples discussed: HTH and HTT. For HTH, we have that H = H, TH != HT, HTH = HTH, so we get 2 + 2^3 = 10. For HTT, we have that T != H, TT != HT, HTT = HTT, so we get 2^3 = 8.

Florida State University College of Law Research Center Epidemiology There is a test for a disease that is 99% accurateThere is a test for a disease that is 99% accurate You test one person randomly – They test positive – What are the odds they have the diseaseYou test one person randomly – They test positive – What are the odds they have the disease

Florida State University College of Law Research Center Rarity of the disease Let’s say the disease is pretty rare, that only 1 in 10,000 people have the diseaseLet’s say the disease is pretty rare, that only 1 in 10,000 people have the disease

Florida State University College of Law Research Center Rarity You test one million people. At that rarity 100 people would have the disease and since the test is 99% accurate, it would correctly identify 99 people as having the disease and it would miss one.You test one million people. At that rarity 100 people would have the disease and since the test is 99% accurate, it would correctly identify 99 people as having the disease and it would miss one.

Florida State University College of Law Research Center Rarity You test one million people for the disease, since only about 100 will have the disease the overwhelming majority of the 1,000,000 people will not, but since the test is 99% accurate it will falsely identify 10,000 people as having the disease.You test one million people for the disease, since only about 100 will have the disease the overwhelming majority of the 1,000,000 people will not, but since the test is 99% accurate it will falsely identify 10,000 people as having the disease.

Florida State University College of Law Research Center Rarity What are the odds that the one individual who was initially tested, actually has the disease?What are the odds that the one individual who was initially tested, actually has the disease? Considerably less than 1%.Considerably less than 1%.

Florida State University College of Law Research Center Sally Clark Clark’s first son died a few weeks after birthClark’s first son died a few weeks after birth Clark’s second son also died shortly after birthClark’s second son also died shortly after birth Both cases appeared to be from Sudden Infant Death SyndromeBoth cases appeared to be from Sudden Infant Death Syndrome

Florida State University College of Law Research Center Pediatrician A pediatrician testified that two children dying from SIDS from and educated and affluent family (which the Clark family was) was very unlikelyA pediatrician testified that two children dying from SIDS from and educated and affluent family (which the Clark family was) was very unlikely

Florida State University College of Law Research Center Pediatrician SIDS occurs in non-smoking healthy household at a rate of about 1/8500

Florida State University College of Law Research Center Pediatrician That two SIDS death would occur at a rate of 1/8500 X 1/8500 or about 1 in 73, 000,000 births.That two SIDS death would occur at a rate of 1/8500 X 1/8500 or about 1 in 73, 000,000 births. It was presented to the jury that the chances that she was innocent was 1 in 73,000,000It was presented to the jury that the chances that she was innocent was 1 in 73,000,000

Florida State University College of Law Research Center Conviction Sally Clark was convictedSally Clark was convicted

Florida State University College of Law Research Center Problems Are there any statistical problems in this analyis?Are there any statistical problems in this analyis?

Florida State University College of Law Research Center First Problem One problem is that the relative rareness of parents who kill their children was not presented.One problem is that the relative rareness of parents who kill their children was not presented. This is essentially the same problem we saw with the epidemiological problem the test for a disease that is 99% accurate.This is essentially the same problem we saw with the epidemiological problem the test for a disease that is 99% accurate.

Florida State University College of Law Research Center Second Problem No evidence of independence was presented at the trial.No evidence of independence was presented at the trial. There are both genetic and environmental conditions that increase the risk of SIDSThere are both genetic and environmental conditions that increase the risk of SIDS

Florida State University College of Law Research Center Staph Infection In this case it was revealed on appeal that one of the children had a staph infection at the time of death which was probably contributory to the death.In this case it was revealed on appeal that one of the children had a staph infection at the time of death which was probably contributory to the death. (Somehow at the original trial the prosecution was aware of this but the defense was not.)(Somehow at the original trial the prosecution was aware of this but the defense was not.)

Florida State University College of Law Research Center Released After three years in prison her second appeal was successful and she was released.After three years in prison her second appeal was successful and she was released.

Florida State University College of Law Research Center Ending Unfortunately this does not have a happy endingUnfortunately this does not have a happy ending

Florida State University College of Law Research Center Books in the Research Center Elementary Statistics – QA W Elementary Statistics – QA W Introduction to the Practice of Statistics – AQ M Introduction to the Practice of Statistics – AQ M Understanding Statistics – an Introduction for the Social Sciences – HA2 W Understanding Statistics – an Introduction for the Social Sciences – HA2 W

Florida State University College of Law Research Center Statistics for Dummies

Florida State University College of Law Research Center The Complete Idiot’s Guide to Statistics

Florida State University College of Law Research Center The Practically Cheating Statistics Handbook

Florida State University College of Law Research Center Statistics How To

Florida State University College of Law Research Center

SPSS 01.ibm.com/software/analytics/spss/ 01.ibm.com/software/analytics/spss/ 01.ibm.com/software/analytics/spss/ 01.ibm.com/software/analytics/spss/

Florida State University College of Law Research Center

Card Punch Machine

Florida State University College of Law Research Center

SPSS Cost

Florida State University College of Law Research Center SPSS Academic

Florida State University College of Law Research Center SAS

SAS Cost

Florida State University College of Law Research Center STATA

STATA Cost

Florida State University College of Law Research Center Sources How juries get fooled by statistics by Peter DonnellyHow juries get fooled by statistics by Peter Donnelly A Judge’s Deskbook on the Basic Philosophies and Methods of Science A Judge’s Deskbook on the Basic Philosophies and Methods of Science Federal Judicial Center Judicial Center

Florida State University College of Law Research Center Sources Jury Understanding of DNA Evidence: An Empirical Assessment of Presentation Formats for Trace Evidence with a Relatively Small Random Match Probability Understanding of DNA Evidence: An Empirical Assessment of Presentation Formats for Trace Evidence with a Relatively Small Random Match Probability The Use of DNA statistics in criminal trials 46H1XKM- C&_user= &_coverDate=08%2F28%2F2002&_rdoc=1&_fmt=&_orig=sea rch&_sort=d&view=c&_version=1&_urlVersion=0&_userid= &md5= ae6342fa95b322c3af3ea07The Use of DNA statistics in criminal trials 46H1XKM- C&_user= &_coverDate=08%2F28%2F2002&_rdoc=1&_fmt=&_orig=sea rch&_sort=d&view=c&_version=1&_urlVersion=0&_userid= &md5= ae6342fa95b322c3af3ea H1XKM- C&_user= &_coverDate=08%2F28%2F2002&_rdoc=1&_fmt=&_orig=sea rch&_sort=d&view=c&_version=1&_urlVersion=0&_userid= &md5= ae6342fa95b322c3af3ea H1XKM- C&_user= &_coverDate=08%2F28%2F2002&_rdoc=1&_fmt=&_orig=sea rch&_sort=d&view=c&_version=1&_urlVersion=0&_userid= &md5= ae6342fa95b322c3af3ea07

Florida State University College of Law Research Center The End