Summer I, 2016







Lecture 
Date 
Lecture & Lab Topics 
Readings, from Bertsekas unless otherwise noted 
Homeworks and Tests 
Labs 
1  M 5/23  Administrative matters; Goals of the course; Motivating Examples: Why should a computer scientist know probability and statistics? Introduction to Classical Probability: Coin flips and random choices. Set theory and probability. 
Here is a link to an article on traffic deaths after 9/11: HTML Here is the wiki page explaining the "Base Rate Falacy" (look at Example 1, on breathalyzer tests): HTML Here is chapter one of The Drunkard's Walk (the whole thing is worth reading, but I will talk about the flight instructors example on pages 7 and 8): PDF Just for Fun: Here is a short YT video with various clips from movies which involve probability (we will return to the Monty Hall Problem, the first clip, in a later lecture): HTML Sections 1.1  1.2 (PDF) 

2  T 5/24  Classical Probability  Sections 1.1  1.2 (PDF)  
3  W 5/25 



R 5/26  
R 5/26  Lab 01: Generating random numbers and running simulations  
4  T 9/15  The general Inclusion/Exclusion Principle; Combinatorics and counting finite sets; Multiplication principle and tree diagrams; The Monty Hall Problem (application of the Multiplication Principle); Choosing with and without replacement; Permutations. 
Read this short article on the InclusionExclusion Principle: HTML and then read page 48 (skipping the proof if you like....) in the textbook. Sections 1.7 (main reading) Also Google "probability tree diagram" and read the first link (easy) and then read sections 14.1 and 14.2 of the following analysis of the "Monty Hall Problem": PDF 

5  R 9/17  Counting principles continued; permutations and combinations; accounting for duplicates; applications to classical probability. 
Section 1.8  
M 9/21  Lab 02: Computing with permutations and combinations; simulation continued.  Read about Pascal's Triangle and its relationship to C(N,K) here.  
6  T 9/22  Counting concluded: combinations and subsets; accounting for repetitions; multinomial coefficients;  Section 1.8, Read this link on Permutations with Repetitions; Section 1.9 

7  R 9/24  Discrete nonequiprobably sample spaces; Histograms vs distributions; Conditional Probability  Read about Histograms here: Section 2.1 

M 9/28  Lab 03: Drawing probabilities in Python: PMFs and CDFs  
8  T 9/29  Conditional Probability; Independence  Section 2.2  
9  R 10/1  Bayes Theorem, Discrete Random Variables; Distributions, PMFs and CDFs  Read about Bayes Theorem here: HTML Just read the first two screenfuls or so, with the background, statement of the theorem and the example about Addison. Read chapter 3.1 up to page 98 on Discrete Random Variables. This is just a way of formalizing what we have already been doing! 

M 10/5  Lab 04: Introduction to Pandas and data analysis  
10  T 10/6  Multiple Random Variables on same sample space; Properties of random variables: mode, expected value/mean  Our textbook spreads out the various characteristics of random variables, and I would rather you read Chapter Five from the Schaum's, which I provide since not all of you will have bought it: PDF This reading uses f(x) instead of p(x) for the PMF, but otherwise it is fairly consistent with what we have been doing. 

11  R 10/8  Properties of random variables: moments; variance and standard deviation, skewness, kurtosis. Uniform Distributions, Bernoulli Trials, Binomial Distribution 
Finish reading Schaum's on properties of random variables. Read pp. 9799 in DeGroot, or look at the StatTrek page on Binomial: HTML 

T 10/13  Monday Schedule; Lab 05  
12  R 10/15  Characteristics of the Binomial: Mean, Mode, Variance, Standard Deviation; Binomial Experiments; Why is the binomial so important? Generalizations of the Binomial: Multinomial, Hypergeometric Distributions 
Read about Multinomial and Hypergeometric Distributions in sections 5.9 and 5.3 of the textbook; just read to get the basic idea (these are generalizations of the binomial)
OR, read pages 1934 of the Schaum's Outline (easier) here: PDF 

M 10/19  Lab 06: Fitting distributions to data; Generating random variates by simulation.  
13  T 10/20  Other discrete distributions: Poisson  Read about Poisson in Section 5.4 of the textbook; this whole section is very good, but you should skip all the proofs, and skip Theorems 5.4.3 and 5.4.4. The Wiki page on the Poisson is also good: HTML, read up through the Properties section for mean, variance, & mode. 

14  R 10/22  Conclusions on discrete distributions: Poisson concluded; the Geometric distribution; the Negative Binomial distribution. Continuous random variables: Uniform distribution, why CDFs are important; integrals in place of summations 
Read about the Negative Binomial and the Geometric in 5.5; we will use the formula at the top of p.298 for the PMF; skip Theorems 5.5.2 and 5.5.3 but look carefully at Theorem 5.5.5 (the Memoryless Property of Geometric). You can also look at these in the summary of distributions which I have linked at the top of the page.


M 10/26  Lab 07: Generating random variates by the inverse method; approximating the Binomial with the Poisson  
15  T 10/27  Continuous random variables: Uniform distribution, why CDFs are important; integrals in place of summations Normal Distribution 
Remind yourself about the properties of continuous distributions by looking through section 3.2. The wiki page on continuous distributions is also useful: HTML If you forget how integrals work, you might want to glance over the Wiki article: HTML Read pp.302303 on the motivation and definition of the Normal Distribution (Def 5.6.1), and look at Definition 5.6.2 on the Standard Normal Distribution. The Wiki page on the normal distribution is excellent: HTML 

16  R 10/29  Approximating the binomial with the Normal distribution; Exponential Distribution; relationship between Exponential and Poisson.  Read about the normal approximation to the binomial here: HTML On Exponential: Read pp.3214; also see the Wiki Page: HTML up through "Memoryless Property" and also read "Occurrences of Events" 

M 11/2  No Lab!  
T 11/3  Conclusions on Distributions; Theoretical results about distributions: Cheveshev's Inequality; Law of Large Numbers; Central Limit Theorem  
17  R 11/5  Midterm  
M 11/9  No lab!  
18  T 11/10  Joint random variables; Independent RVs  Please look at the section "Discrete Joint Distributions" in 3.4 and then read 3.5 on Marginal Distributions. As usual, the Wiki article on this is very good: https://en.wikipedia.org/wiki/Joint_probability_distribution 

19  R 11/12  Covariance, Correlation, Autocorrelation  Read section 4.6 in the textbook (again, skipping all the proofs, and understanding that we are only really considering the discrete case) The Schaum's Outline has a brief treatment of these topics starting on page 129 here: PDF And, again, the Wiki article is useful: HTML


M 11/16  Lab 08: Computing Covariance and Correlation; Correlation in data sets  
20  T 11/17  Regression and Curve Fitting  The Schaum's treatment of these topics in Appendix A6, starting on p.257, is fairly good: PDF The Wiki article on "Simple Linear Regression" is also good: HTML


21  R 11/19  Guest Lecture by Steve Homer: Probabilistic Algorithms  
M 11/23  Lab 09: Displaying Joint Distributions  
22  T 11/24  Class cancelled, I was sick!  
23  R 11/26  No Class: Thanksgiving Break  
M 11/30  Lab 09 concluded.  
23  T 12/1  Statistics: Basic framework based on CLT; Presentation of final project  
24  R 12/3  Statistics: sample distribution of means; confidence intervals  Reading: PDF  
M 12/7  Lab 10: Work on Final Project  
25  T 12/8  Statistics: Hypothesis Testing  Reading: PDF  
26  R 12/10  Quiz 3; Course Evaluations  Quiz 3 Solution: PDF  
R 12/17  Final Exam 12:30  2:30pm  
Saturday 12/19 12 noon  Final Project due, 12 noon 