Applied multivariate methods are an increasingly important tool in applied machine learning and statistics. We will start with reviewing important facts from matrix algebra and learning about the multivariate normal distribution. Then we will delve into unsupervised and supervised learning approached for multivariate data, where the data may or may not be normally distributed. The data is often highly dimensional in the covariates or parameter space, calling for dimension reduction. We will explore a range of approaches starting with factor analysis, principal component analysis, and then moving along to data mining techniques such as classification and clustering methods. Finally, we will explore Bayesian methods for multivariate data and the strengths and weaknesses of both approaches.
Readings are posted at Course Topic List Page.
T/Th: 1:30PM-2:50PM, location PH 125C
Rebecca C. Steorts
Baker Hall 132 K
beka [at] cmu [dot] edu
Office hours: Tuesday: 3-4pm, Wednesday: 11:30-12:30 (Baker Hall 132 K)
Rafael Stern
8115 Wean Hall
rafaelst [at] cmu [dot] edu
Office hours: Monday: 12--1 pm; Thursday: 10--11 am
Nicolas Kim
Porter 117
nicolask [at] stat [dot] cmu [dot] edu
Office hours: Tuesday: 11 am--12 pm; Wed: 3--4 pm
Statistics 401. Students are expected to be very familiar with R. Please see Prof. Steorts if unsure whether you meet the requirements.
The course consists of scribing, readings, lectures, discussions, homework's, and take-home exams. There will be no make up homework assignments or exams. You are responsible with being in class and being responsible for finding out what happened if you missed class. There is a temporary schedule on the course webpage, however, all assignments and topics are subjects to change.
Scribing is a form of taking notes. Each of you will scribe once during the semester and this will count as a homework grade. Please use LaTex to prepare scribe notes, and please use the template. Below you will find the completed scribe notes. If you are not familiar with Latex (please see http://www.latex-project.org/ for more information and downloading for your OS). This is a great way to write up reports and display mathematical equations and graphical plots.
Most questions should be directed to the Google group and Discussion Forum for the course. The webpage can be found at Multivariate Google Groups .
Posting via email is done through: multivar_cmu_14 [at] googlegroups [dot] com