## 36464/36664: Applied Multivariate Methods

Please use the homework template to submit homework's (compile to pdf format. If you have not used Latex before, you may find \url{https://pangea.stanford.edu/computing/unix/formatting/latexexample.php} helpful for getting started.

The notes will be due to Rafael, Nick, and myself (via email) one week after the lecture (by 10 am that day).

### Syllabus

1. ##### Introduction to Applied Multivariate Methods (with a review of matrix algebra)
(Tuesday January 14 1:30PM)
[scribe notes] [Ch1:Multivariate Notes] [Lecture1 Slides]

• Please begin reading the Multivariate Notes posted online. Slides will be posted after class. Be sure to review matrix algebra on your own if this is unfamiliar.
2. ##### More Multivariate Analysis
(Thursday January 16 1:30PM) [scribe notes] [Lecture2 Slides] [Howework 1] [Howework 1 Solutions] [Longer Proof of Theorem, Slides 17--19]

• Please read/review the Matrix notes as needed [Matrix Cookbook] and use these as a source if you are having trouble remembering some matrix results in the course.
3. ##### The Multivariate Normal Distribution and Properties
(Tuesday January 21 1:30PM) [scribe notes] [Lecture3 Slides]

• Read any scribe notes posted and Ch 1 notes if not finished. Review the slides. Don't forget that HW 1 is due at Midnight on Wednesday 22 at 11:59 pm.
4. ##### Contour Plots and Intro to PCA
(Thursday January 23 1:30PM) [scribe notes] [Ch2: PCA Notes] [PCA R code] [Lecture4 Slides] [Howework 2] [Howework 2 Solutions] [Howework 2 SAIPE data]

• Please read the PCA material in the James et al. (2013) book and the PCA notes here online.
5. ##### More PCA
(T January 28 1:30PM) [Tues scribe notes] [Lecture5 Slides]

(Th January 30 1:30PM) [Lecture6 Slides] [Howework 3] [Howework 3 Solutions] [Thurs scribe notes]

• Please read the PCA material in the James et al. (2013) book and any notes that are posted online. We examples on PCA (time permitting). Please bring your laptops if you want to try and follow along. Note: The office hours for me have changed to Tuesdays (3-- 4 pm) and Wednesdays (11:30 -- 12:30). See the updated syllabus for TA updated office hours.
6. ##### Factor Analysis
(T/Th February4/6 1:30PM) [scribe notes] [Ch3: Factor Analysis Notes] [Lecture7 Slides] [scribe notes]

• Please read the Factor analysis material posted online. We will cover examples on Factor analysis (time permitting). Please bring your laptops if you want to try and follow along.

Take home exam 1 will cover material up to this point! You MAY NOT work together on the take home exam.

7. ##### Introduction to classification methods: unsupervised and supervised learning
(Tuesday Feb 11 1:30PM) [Lecture9 Slides] [scribe notes]

• Please read Chapter 4 through page 150 on logistic regression, LDA and QDA.
8. ##### LDA and QDA
(Thursday Feb 13 1:30PM) [Lecture10 Slides] [scribe notes]

• Please read Chapter 4 through page 150 on logistic regression, LDA and QDA.
10. ##### Introduction to Regression and Classification Trees
(T/Th Feb 18 and Feb 20 1:30PM) [Ch5: Trees Notes] [Lecture11 and 12 Slides] [scribe (lecture 11) notes]

scribe-lecture12-chang-kim.pdf
11. ##### Optional office hours during class: Take home exam
(Tues Feb 25 1:30PM)

12. ##### No class: Take home exam
(Thurs Feb 27 1:30PM)

13. ##### Classification Trees
(Tues March 4 1:30PM) [Ch5: Trees Notes] [Lecture13 Slides] [scribe notes]

14. ##### Bootstrapping and Bagging
(Thursday March 6 1:30PM) [Lecture 14 Slides] [scribe notes]

15. ##### Random Forests
(Tues March 18 1:30PM) [Lecture15 Slides]

16. ##### Introduction to Clustering: Part II
(Tues March 25 1:30PM) [Lecture17 Slides] [scribe notes]

Take home exam 2 will cover material up to this point! You MAY NOT work together on the take home exam. Take home exam two will be posted to blackboard on Friday March 28 and will be due at 11:59 pm on Friday April 4. Please follow the instructions as posted on the exam. Please see class emails for clarification questions on the take home exam. There have been no typos found thus far.

17. ##### No class
(Thurs March 27 1:30PM) [Lecture18 Slides]
• Please read the clustering notes that are posted. Please read the notes and slides I post on hierarchical clustering. You will be responsible for these even those class is canceled on March 27. Lecture slides will be done for this class on April 8 and posted then. No slides for this class.
18. ##### Advanced Data Analysis Class on PCA and Factor Analysis
[Lecture19 R Code] [scribe notes]

(Tues April 1 1:30PM)

19. ##### Advanced Data Analysis Class on Recommendation Systems
(Thurs April 3 1:30PM) [Recommender Systems Slides] [Recommender Systems R Code] [Recommender Systems Data] [scribe notes]

20. ##### Hierarchical clustering
(Tues April 8 1:30PM) [Lecture 20 Slides] [scribe notes]
• Please read the clustering notes that are posted. Please read the notes and slides I post on hierarchical clustering. Homework 8 goes with this lecture and refers back to Homework 7.
21. ##### Intro to Bayesian Methods
[Bayes Notes] [Lecture 21 Slides] (Tuesday April 15 1:30PM) [scribe notes]

• Please read posted lecture notes and start of Robert and Marin text.
22. ##### Intro to MCMC
[Lecture 21 Slides] [Howework 9] [Howework 9 Solutions] (Thurs April 17 1:30PM) [scribe notes] [scribe notes]

23. ##### More MCMC and Intro to PlA2 Dataset
[Lecture 22 Slides] (Tues April 22 1:30PM) [scribe notes]
24. ##### Convergence Diagnostics and More on MCMC
[Lecture 23 Slides] (Thursday April 25 1:30PM) [scribe notes]
25. ##### Image Analysis and MCMC
[Lecture 24 Slides] (Monday April 28 5:30PM--Make Up Lecture) [scribe notes]

## Detailed Schedule

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

 Tues Jan 14 1. Introduction and why multivariate models? Thurs Jan 16 2. More about multivariate models Tues Jan 21 3. More about multivariate models Thurs Jan 23 4. Contour plots and Intro to PCA. Tues Jan 28 5. PCA Thurs Jan 30 6. PCA Tues Feb 4 7. Factor Analysis Thurs Feb 6 8. Factor Analysis Tues Feb 11 9. Introduction to classification methods. Thurs Feb 13 10. LDA and QDA Tues Feb 18 11. Introduction to Regression and Classification Trees Thurs Feb 20 12. No class: Take home exam Tues Feb 25 13. No class: office hours Thurs Feb 27 14. No class: take home exam Tues Mar 4 15. Classification Trees Thurs Mar 6 16. Bootstrapping and Bagging Tues Mar 11 (Spring break, no class) Thurs Mar 13 (Spring break, no class) Tues Mar 18 17. Random Forests Thurs Mar 20 18. Intro to Clustering . Tues Mar 25 19. Intro to Clustering II Thurs Mar 27 20. No class Tues Apr 1 21. R Lab Thurs Apr 3 22. R Lab Tues Apr 8 23. Intro to Bayesian Analysis Thurs Apr 10 (Spring carnival, no class) Tues Apr 15 24. Intro to Bayesian Analysis Thurs Apr 17 25. Intro to Gibbs Sampling Tues Apr 22 26. Bayesian special topics: TBD Thurs Apr 24 27. Bayesian special topics: TBD Tues Apr 29 28.Bayesian special topics:TBD Thurs May 1 29. TBD

Top