This course concerns the foundational mathematical principles that guide the practice of statistical inference. Topics include properties of estimators (sufficiency, efficiency), methods of estimation (method of moments, maximum likelihood), hypothesis tests, confidence intervals, permutation testing, the bootstrap, linear models, and Bayesian methods. To succeed in this course you should have experience with discreet and continuous probability, integral calculus, linear algebra, and programming in R.
Andrew Bray
Library 304
Office hours: Wednesday 3 - 5 pm, Friday 3 - 5 pm
We meet for lecture MWF 1:10 - 2 pm in Library 389. Occasional class periods will feature group problem solving, which will require laptops, so keep your eyes out for those. Most class periods will not require a computer.
Probability and Statistics 4th Edition DeGroot and Schervish
Additional material will be drawn from:
- Mathematical Statistics and Data Analysis by John Rice
- Statistical Inference by Casella and Berger
- Mathematical Statistics Notes by Albyn Jones
Weekly problem sets will be due on Friday in class. These should be done in RStudio (either locally or on the server) using either the .Rmd or .Rnw file format to weave together text and math (via Latex) and R code. See the problem sets directory for an example template. Please output your problem set as a pdf, print it out, staple it, and bring it to class on Friday.
There will be two midterms and a final. Each exam will be followed by a paper conference with me lasting 20 minutes where we'll talk through your exam and work through any difficult areas. Exam dates are TBA.