News

[4/27/13]

The final review problems are posted here. Don't forget to review problem set 5, problem set 6, and the midterm 2 review set. You should at least look at the solutions to those.

[4/23/13]

Problem set 6 has been posted. This is the last problem set. The final exam will be on May 3 9:30am - 12:30pm. The exam is cumulative in the sense that everything we learned so far was built on the materials we covered at the beginning. The review set will be posted by Friday. We are almost there guys. Hang in there.

[4/9/13]

Lecture slides from today have been posted.

[4/5/13]

Hope everyone got their redemption at the midterm today. Problem set 5 has been posted.

[3/15/13]

Slides and the demo from today have been posted.

[3/8/13]

Lab 2 has been posted. It's due March 15. Lab 1 is also due March 15. Look at the updated link for more instruction.

[2/19/13]

The midterms have been graded, and they were a disappointment. Email Te if you want to know the score. The midterms will be handed back in class on Friday after we're back from the break. Problem set 3 has been posted and due March 8.

[2/8/13]

Midterm review questions were posted. R stuff will NOT be on the exam. Good luck studying.

[2/5/13]

Lab 2 is postponed to make room for you to prepare for the midterm, which is on Feb 15.

[1/31/13]

Problem set 2 is now live. I'm still working on Lab 2. It should be ready some time this weekend. Lab 2 is significantly shorter than Lab 1. The tutorials should take half an hour.

[1/24/13]

Lab 1 and the accompanying tutorials are now available. Lab 1 will be due Feb 1. There will be no problem set due Feb 1. The tutorials are two hours long total and quite challenging. Get to those as soon as you can.

[1/20/13]

Problem set 1 is out and due January 25 in class.

[12/20/12]

The class will be in Goldsmith 226. Tuesday and Friday 11AM - 12:30PM.

[11/28/12]

Lab 0 is now up on the site for testing purposes.

[11/24/12]

Welcome to your second quant class. We will do some probability, statistics, and quite a bit of computing. It will be fun, and you will learn a lot.

Course materials

This should accurately show what happened in the past but it might not accurately reflect what will be covered in the future dates. Every problem set is due in class on Friday (one week after it's assigned). You can also find the materials in the course Google Drive.

Week 1 (Jan 15)

Basic vocab in probability theory. Basic combinatorics.
Lab : Install R
handout1 | handout2 | problem set 1 (due Jan 25)

Week 2 (Jan 22)

Categorical distribution. Intro to probability model
Lab : Computing probabilities from data frames
slides | lab 1 (due Feb 1)

Week 3 (Jan 29)

Conditional probability
problem set (due Feb 8)

Week 4 (Feb 5)

Programming basics
Midterm review set

Week 5 (Feb 12)

Review (Feb 12) and midterm (Feb 15)

Week 6 (Feb 19)

February break

Week 7 (Feb 26)

Bayes' Rule
problem set 3 (due March 8)

Week 8 (Mar 5)

Programming in R. Chi-squared test.
Lab : Chi-squared test
Programming in R slides | chi-squared test demo | lab 2 (due March 15)

Week 9 (Mar 12)

Joint categorical distribution. Bernoulli distribution.
Lab : Chi-squared test of independence
hypothesis testing slides | chi-squared test spreadsheet |
joint categorical distribution slides | chi-squared test of independence spreadsheet |
problem set 4(due March 22)

Week 10 (Mar 19)

Binomial distribution, Review
review slides | midterm review problems

Week 11

Spring break

Week 12 (Apr 5)

Midterm 2
problem set 5 (due April 15)

Week 13 (Apr 9)

Beta distribution; Poisson distribution
Lab : Beta distribution and Poisson model
beta distribution slides | lab 3 (due April 22)

Week 14 (Apr 16)

Exponential distribution

Week 15 (Apr 23)

Normal distribution
problem set 6 (due May 3)

Week 16 (Apr 30)

Wrap up and Final exam
final review problems

Lab tutorial

Lab 0

Using R as a calculator: tutorial
Lab assignment 0 due before the end of Jan 19 on Latte

Lab 1

Variable assignments and functions: tutorial
Vector, for-loop, if statement: tutorial
Example using vector and for-loop: tutorial
Data frame: tutorial
Plotting in R: tutorial
Lab assignment 1 due before the end of Feb 1 on Latte

Course information

Location : Goldsmith 226

Time : Tuesday and Friday 11AM - 12:20PM

Instructor : Te Thamrongrattanarit (tet@brandeis.edu)

Teaching assistant : Wendy Xu (wendyxu@brandeis.edu)

Course description

We will explore key statistical concepts and probabilistic models motivated through problems and examples from daily life, news articles, and research articles. How do we know that an election result is still 'too close to call'? How did Nate Silver predict the election results so accurately? How does Netflix know what movie we like? Is probability really taken into account into a game of poker by the player? Do dietary supplements actually make us fitter? These questions will be answered from the intersection of statistics and probability. We will cover fundamental concepts such as mean, expected value, variance, conditional probability, regression models, various probabilistic models, hypothesis testing, and decision theory. We will explore how to use these concepts to meaningfully organize, analyze, and summarize the data and draw conclusions to explain phenomena that seem to happen at random.

In addition to theoretical foundation, the course will also emphasize computation and data visualization as a means to convey conclusions or arguments that can be drawn from statistical analyses. We will use statistical programming language R to analyze several real-world datasets and visualize the results as the hands-on component of the course. Students will be able to critically analyze non-traditional data visualization techniques used in the media (infographics) and conventional figures found in scientific articles. At the end of the course, students will become a critical consumer and an effective producer of statistical information.

Textbooks

R In a Nutshell by Joseph Adler (2nd edition)-- This book will be used as reference to aid you with the lab assignments. It will save you a lot of time googling things.

Master Math: Probability by Catherine A. Gorini -- We will loosely follow this textbook. It's inexpensive, readable (without treating you like a dummy), and sufficiently rigorous for our purposes.

Course format and grading

This class is not ye-olde math course, where you sit and write down what's on the board. To keep things interesting, you will be doing a bunch of different things for this class.

Problem sets (20%). Wendy will be leading the problem session. The first hour, we will be going over some of the problems from the problem set together. The rest of the time will be 'working office hours,' where you can work together and ask the TA questions as they come up. You are required to do the problem set, but you are not required to attend the problem session. However, the attendance will help if your final scores are on the border between two grades (e.g. if you're in between B+ and A-, the attendance will bump you up to A-)
Lab assignments (25%). The video tutorial and accompanying lab assignments will be posted every other week or so. You will be working on these at your own pace outside of class. For each week, one of you will be assigned to present the result from the lab assignment.
Tests (50%). There are two midterms (10% each). They are right before we leave for February break and Passover break respectively. The final exam (30%) is cumulative and scheduled by the university. All exams are open notes.
Lecture, problem session, and discussion (5%). Being a good student will award you this 5%. Show up to class and the problem sessions and this 5% is yours

Topics

Counting, permutation, and probability
Joint, marginal, and conditional probability
Bernoulli and Binomial distributions
Hypothesis testing: binomial, chi-squared
Poisson distribution and exponential distribution
Normal distribution
Law of large number and central limit theorem