Advanced Methods for Data Analysis: Spring 2014

Statistics 36-402/36-608

Instructor: Ryan Tibshirani (ryantibs at cmu dot edu)

TAs:
Jisu Kim (jisuk1 at andrew dot cmu edu)
Robert Lunde (rlunde at andrew dot cmu dot edu)
Sonia Todorova (sktodoro at andrew dot cmu dot edu)

Lecture times: Tuesdays and Thursdays 10:30-11:50am, Wean 7500

Office hours:
RT: Wednesdays 3-4pm, Baker 229B
RL: Thursdays 3:30-4:30pm, Porter 117
ST: Mondays 3:30-4:30pm, Porter A20

Course syllabus: PDF

Go to: Lectures | Assignments | Schedule

Lecture notes

Introduction and regression
- Lecture notes
- Shalizi Chapter 1
- R files: intro.R, nonlin.Rdata
Introduction and regression (cont'd)
- (Same materials as previous lecture)
The truth about linear regression
- Lecture notes
- Shalizi Chapter 2
- R files: ch02.R (from Shalizi Chapter 2)
Error and validation
- Lecture notes
- Shalizi Chapter 3
- R files: ch03.R (from Shalizi Chapter 3)
Error and validation (cont'd)
- (Same materials as previous lecture)
- + R files: errval.R
Kernel regression
- Lecture notes
- Shalizi Chapter 4
The bootstrap
- Lecture notes
- Shalizi Chapter 6
- R files: bootstrap.R
The bootstrap (cont'd)
- (Same materials as previous lecture)
Degrees of freedom
- Lecture notes
- R files: df.R
Degrees of freedom (cont'd)
- (Same materials as previous lecture)
Smoothing splines
- Lecture notes
- Shalizi Chapter 8
- R files: smoothspline.R
Smoothing splines (cont'd)
- (Same materials as previous lecture)
Additive models
- Lecture notes
- Shalizi Chapter 9
- R files: addmodels.R
Catch up / review
- (No notes)
Inference with linear smoothers
- Lecture notes
- R files: linsmooth.R
Inference with linear smoothers (cont'd)
- (Same materials as previous lecture)
Logistic regression
- Lecture notes
- Shalizi Chapter 12
- R files: logreg.R
Generalized linear models
- Lecture notes
- Shalizi Chapter 13
- R files: glm.R
Generalized linear models (cont'd)
- (Same materials as previous lecture)
Principal components analysis
- Lecture notes
- Shalizi Chapter 17
- R files: pca.R, playerstats.Rdata
Principal components analysis (cont'd)
- (Same materials as previous lecture)
Other dimension reduction techniques
- Lecture notes
Clustering
- Lecture notes
- R files: clustering.R, kclust.R
Clustering (cont'd)
- (Same materials as previous lecture)
Clustering (cont'd)
- (Same materials as previous lecture)
High-dimensional regression
- Lecture notes
High-dimensional regression (cont'd)
- (Same materials as previous lecture)
- + R files: highdim.R, bvsim.R

Top

Assignments

Homework 1, due Thurs Jan 23
R files: nonlin.Rdata
Homework 2, due Tues Feb 4
R files: penn-table.csv, cv_bws_npreg.R
Homework 3, due Thurs Feb 13
R files: abalone.csv
Homework 4, due Tues Feb 25
R files: abalone.csv
Midterm exam 1 (take-home), due Thurs Mar 6
R files: check your email
Homework 5, due Thurs Mar 20
R files: abalone.csv
Homework 6, due Tues Apr 1
R files: n88_pol.csv
Homework 7, due Tues Apr 8
Homework 8, due Tues Apr 22
R files: digits.Rdata, plot.digit.R
Homework 9, due Thurs May 1
R files: hitters.Rdata,
Final exam (take-home), due Thurs May 8
R files: check your email

Top

Schedule

Here is the planned class schedule. It is subject to change, depending on time and class interests.

Tues Jan 14	1. Introduction and regression
Thurs Jan 16	2. Introduction and regression (cont'd)
Tues Jan 21	3. The truth about linear regression
Thurs Jan 23	4. Error and validation	Homework 1 due
Tues Jan 28	5. Error and validation (cont'd)
Thurs Jan 30	6. Kernel regression
Tues Feb 4	7. The bootstrap	Homework 2 due
Thurs Feb 6	8. The boostrap (cont'd)
Tues Feb 11	9. Degrees of freedom
Thurs Feb 13	10. Degrees of freedom (cont'd)	Homework 3 due
Tues Feb 18	11. Smoothing splines
Thurs Feb 20	12. Smoothing splines
Tues Feb 25	13. Additive models	Homework 4 due
Thurs Feb 27	14. Catch up / review	Take-home exam out
Tues Mar 4	15. Inference with linear smoothers
Thurs Mar 6	16. Inference with linear smoothers (cont'd)	Take-home exam due
Tues Mar 11	(Spring break, no class)
Thurs Mar 13	(Spring break, no class)
Tues Mar 18	17. Logistic regression
Thurs Mar 20	18. Generalized linear models	Homework 5 due
Tues Mar 25	19. Generalized linear models (cont'd)
Thurs Mar 27	20. Principal components analysis
Tues Apr 1	21. Principal components analysis (cont'd)	Homework 6 due
Thurs Apr 3	22. Other dimension reduction techniques
Tues Apr 8	23. In-class exam	Homework 7 due; in-class exam
Thurs Apr 10	(Spring carnival, no class)
Tues Apr 15	24. Clustering
Thurs Apr 17	25. Clustering (cont'd)
Tues Apr 22	26. Clustering (cont'd)	Homework 8 due
Thurs Apr 24	27. High-dimensional statistics
Tues Apr 29	28. High-dimensional statistics (cont'd)
Thurs May 1	29. High-dimensional statistics (cont'd)	Homework 9 due; take-home final out
Thurs May 8		Take-home final due

Top