University of WisconsinMadison
Statistics 3273: Advanced Data Analysis with R
Check www.stat.wisc.edu/~jgillett/3273 for updates to this tentative syllabus.
Goals
Students will integrate R with high performance computing
tools to do scientific computing at an introductory level. Here is a
course map.
Teachers  
Name  Office  Office hour  Email (please use our Q&A forum for most things) 
Yang, Bo  Medical Sciences Center 1227  Thur 11:5012:50 am or by appointment  byang76@wisc.edu 
Li, Qing  Medical Sciences Center 1217A  Tues 3:004:00 pm  qli295@wisc.edu 
TAs  
TA Kim, Yongjoon  kimy@stat.wisc.edu  
Class Times
Lecture 327003 (Teacher Li, Qing)  Tues, Thur, 11:00 am12:15 pm  STERLING 2301 
Lecture 327006 (Teacher Yang, Bo)  Tues, Thur, 1:002:15 pm  STERLING 2301 
Lecture 327009 (Teacher Yang, Bo)  Tues, Thur, 2:303:45 pm  STERLING 2301 
Prerequisite
STAT 327: Intermediate Data Analysis with R 
Textbook
No textbook is required. We'll provide course notes, and we'll read R documentation and write R code. 
Optional Online Reading
R for Data Science by Garrett Grolemund and Hadley Wickham 
Advanced R by Hadley Wickham 
An Introduction to R (pdf) by W. N. Venables, D. M. Smith and the R Development Core Team 
Intro to R video lectures by Google Developers 
R Programming wikibook 
Using
R for Data Analysis and Graphics by
J. H. Maindonald 
The R Inferno by Patrick Burns 
Optional Reference Books
R for Data Science by Garrett Grolemund and Hadley Wickham 
Advanced R by Hadley Wickham 
Introductory Statistics with R by Peter Dalgaard (2008) 
R in a Nutshell by Joseph Adler (2009) 
A Beginner's Guide to R by Alain F. Zuur, Elena N. Ieno, and Erik Meesters (2009) 
Software for Data Analysis: Programming with R by John Chambers (2008) (advanced) 
Modern Applied Statistics with S by W.N. Venables and B.D. Ripley (2002) 
Computing
A laptop is required in class.
Help
Many questions outside of class should be posted at
our Q&A
forum. Please feel free to write answers when you know
them. We are eager to help in class and office hours too.
Grades
These points are available (we might revise this as we write course materials):
≈ 3 R scripts or projects  ≈ 80 
group practice exercises  ≈ 20 
Answer questions in Piazza  ≈ 2 
Total  102 
We'll assign grades according to the percentage scale, A = [92,100], AB = [88,92), B = [82,88), BC = [78,82), C = [70,78), D = [60,70), F = [0,60) (92% of points => A); and according to the percentile scale, A = 70, AB = 60, B = 45, BC = 30, C = 10, D = 5, F = 0 (performing better than 70% of the class => A). Your grade will be the higher of these two grades.
If you anticipate religious or other conflicts with course requirements, or if you require accomodation due to disability, you must notify us during the first two weeks of class. You may not make up missed quizzes, homework, or exams, except in the rare case of a documented, serious problem beyond your control.
We encourage you to discuss the course, including the online quizzes, with others, but you must write the R scripts and the exam by yourself and prevent others from copying your work. (See the UW Academic Misconduct policy.)
Tentative Schedule
Day #: Date  Subject  Homework Due (11:59 p.m.) 
01: Tue 4/10/18  (Install R
and RStudio) (Auditors: email sign up) Optimization (goldenSectionSearch.R) Group practice on optimization (optimization.Rmd, p. 1: optimize()) 
preview hw1, below 
02: Thu 4/12  Optimization, continued (gradientDescent.R, Newton.R, NelderMead.R) Discuss hw1 Finish Group practice (submit one per group), p. 2: optim() 

03: Tue 4/17 
Generic function programming Creating an R package (jgUtilities, jgUtilities_0.1.tar.gz) 
hw1.Rmd (
submit) (login help) 
04: Thu 4/19  Discuss hw2 Debugging (numbersBug.txt, baby.dbinom.R) 

05: Tue 4/24  Profiling, timing, and code efficiency (5profile.R, nflProfile1.R, nflProfile2.R, loopTiming.R) 
hw2.tar.gz ( submit) 
06: Thu 4/26  Discuss hw3 Multicore computing for embarrassingly parallel problems (nfl.R, mandelbrot.R, escape.time.R) 

07: Tue 5/1  Group practice review (submit later)  
08: Thu 5/3 
Calling C++ from R via Rcpp (escapeTime.cpp, mandelbrotRcpp.R) Group practice, continued ( submit one per group) 
hw3.Rmd (submit) 