676
Statistical Learning II
T Th 1
00
- 2
15
pm in Hume Hall 331
Spring 2009
Instructor:
Xin Dang
Office:
Hume Hall 315
Phone:
662-915-7409
Text:
The Elements of Statistical Learning: Data Mining, Inference and Prediction, by Trevor Hastie, Robert Tibshirani and Jerome Friedman, Springer
book website
Course Outline
Bootrap, maximum likehood methods, EM algorithm, Gibbs sampling and bagging.
Additive models, tree models and MARS.
Boosting, additive trees and random forest.
Projection pursuit regression and neural networks.
Support vector machines, generalizing linear discriminant analysis and penalized discriminant analysis.
Unsuperived learing. Clusrer analysis, principle components and factor analysis.
Homework and Project
Homework #1
,
Info of Ozone data
,
Ozone data
R Codes
R programs used in various classroom demonstrations:
logistic additive model fitting
,
Info of CHD data
,
CHD data
Related Readings
Gibbs Sampler
Converagence Properties of EM Algorithm
Bump Hunting in High-Dimension Data
Consistency of Classification Convex Risk Minimization
Greedy Function Approximation a Gradient Boosting machine
Random Forests
SVM for Regression
Any questions/comments/suggestions? Write to
xdang@olemiss.edu