COURSE COVERAGE
Date  Coverage  Homework 

Jan. 6  Introduction to the course and review of some undergraduate probability basics. I recommend Rice's "Mathematical Statistics and Data Analysis", if you are after a reference for this material. 

Jan. 8  Empirical distribution function, qqplots. [R script]  
Jan. 13  GAUSS LAB:
In this class we will examine the topics of the last two classes through simulations  and you will do some associated exercises: [first class][second class] 
Continue learning R  make a list of questions for me if you are having any issues. 
Jan. 15  GAUSS LAB:
We will go over the Jan. 8 R script together, and then you will again be on your own to finish up the exercises and ask questions. 
For the next class we will be back in the lecture room. This means that if you haven't finished going through the script exercises from this week you will need to do so on your own time. 
Jan. 20  Pseudorandom number generators. Generating nonuniform RVs via the inversion method.  [homework] 
Jan. 22 
Generating a geometric RV using the inversion method; rejection sampling; special tricks (including BoxMuller transform). I also introduced the gambda distribution...
Please note:


Jan. 27 
GAUSS LAB:

Make sure that you are in a position to finish the assignment in class on Thursday  work ahead, and identify any problem areas. 
Jan. 29  GAUSS LAB: Finish inclass assignment.  
Feb. 3  Basic Monte Carlo: importance sampling (Section 3.3 in the text).  
Feb. 5  Basic Monte Carlo: stratified sampling (Section 3.2 in the text).  [homework] 
Feb. 10  Introduction to Stochastic Processes: Markov chains, irreducibility
and aperiodicity.
Some references:

[homework] 
Feb. 12  Project groups and topics are due today! More Markov chains: recurrent/transient, positive/null, reversibility and detailed balance. Script for Glum Gary example.  [homework] 
Feb. 1620  READING WEEK  
Feb. 24  Meet in Gauss Lab: A1 is due today! Code will be checked during class
time.
In class assignment: [R script][PDF] 
Homework: prepare your inclass assignment! Here is some additional sample code to help you  it simulated the Gary example Markov chain. 
Feb. 26  Gauss Lab  complete inclass assignment  
March 17  MetropolisHastings algorithm: covered roughly the first 14 pages from Chapter 6 in Introducing Monte Carlo Methods in R by Robert/Casella (ebook available in library)  [homework] 
March 19  Independent MH and comparison with rejection sampling, random walk MH  roughly the first 19 pages of Chapter 6 have now been covered.  [homework] 
March 24  "Review" of maximum likelihood and Bayesian statistics, with the goal of using MCMC MetropolisHastings for a Bayesian problem. [Reference reading][coins example] 

March 26  Finished theory for logistic regression example. Introduction to
the bootstrap (parametric and nonparametric). References for
bootstrap:


March 31  All this week we will be in the Gauss lab. During this time you will need to complete this. I expect that you will need to do some of the work on your own time, in order to have it checked/completed for April 2nd. Please also note that your second and final assignment has also now been posted.  
April 2  Notes for exercise 6.4: [PDF]  
April 7  TEST (WE WILL WRITE THE TEST IN THE GAUSS LAB)  
April 9 


April 14  Permutation inclass assignment:  
April 16  A2 due (code checked inclass) 