Syllabus
Instructor & TAs
Instructor
Jonathan Taylor
- Office: Sequoia Hall #137
- Phone: 723-9230,
- Email
- Office hours: Thursday, 12:00-2:00
Teaching Assistants
Murat Erdogdu
- Email
- Office hours : Monday, 1:00-3:00, Sequoia Hall 220.
Hera He
- Email
- Office hours : Tuesday, 2:30-4:30, Sequoia Hall 207.
Office hours
As a general rule, we ask students NOT to complete the assignments
during TAs’ in office hours. This will be easier if students do not use
laptops while in TAs’ office hours.
Schedule & Location
T-Th 10:30-11:50, 380-380D
Textbook
Statistical
Models
Freedman. Required
Linear Models, with
R
Faraway. Required
Prerequisites
Some familiarity with mathematical statistics at the level of STATS 200,
which is a co-requisite.
Topics covered
- Univariate regression.
- Review of random variables, some linear algebra, law of averages (LLN
and CLT).
- Multivariate regression model. Geometry of least squares.
- Review of random vectors, independence. Multivariate normal
distribution.
- Distribution theory for multivariate regression model under Gauss
model.
- Generalized and weighted least squares.
- Diagnostics / outliers. Data snooping inflates -statistics.
- Model selection, some selective inference.
- Shrinkage methods: ridge regression, LASSO.
- Logistic / probit regression. Poisson regression.
Comparison with STATS191
This course covers many similar topics to STATS191 but in a more
mathematically rigorous way. We may also cover additional models not
covered in STATS191.
Course organization
- All relevant class information, such as homework assignments,
solutions, and organizational matters, will be posted on the
coursework web page.
- Midterm: 2/11, in class.
Evaluation
- homework: 40%
- midterm: 20%
- final exam: 40%
Homework
- You may discuss homework problems with other students and with TAs in
office hours, but you have to prepare the solutions yourself.
- As a general rule, we ask students NOT to complete the assignments
during TAs’ in office hours. This will be easier if students do not
use laptops while in TAs’ office hours.
Computing environment
Most examples will be jupyter notebooks.
Homeworks can be submitted as notebooks.
One option to get started with both python and R is
anaconda, along with the
r-essentials:
conda install -c r r-essentials
# for using R from ipython
conda install -c r rpy2
Final Exam
According to the exam
schedule
our exam is to be held on March 17, at 12:15 PM.