Functional Data Analysis
Links to Lectures (with summary of topics):
Student Presentation 5/1/02: Min Zhang
Student Presentation 4/29/02: Xin Zhao
Student Presentation 4/24/02: Jing Qiu
Lecture 4/22/02 (Finished ICA for discrimination, Polynomial Embedding, Kernel Embedding, Support Vector Machines, Validation of Discrimination)
4/17/02 Class canceled
Student Presentation 4/15/02: Rommel Regis
Lecture 4/10/02 (High dimensional space is strange, FLD expanding dimensions, FLD within class vs. global covariance estimates, ICA for discrimination, toy examples, Corpora Collosa data)
Lecture 4/8/02 (Introduction to HDLSS statistics, Review of FLD vs. Mean Difference, New conceptual model for HDLSS methods, nature of high dimensional Gaussian data)
Lecture 4/3/02 (Fisher Linear Discrimination: Mahalanobis distance, likelihood view. Generalizations: general Gaussian likelihood ratio, multi-class & Principal Discriminant Analysis, FLD for Corpora Collosa data)
Lecture 4/1/02 (Finished ICA nonlinearity toy examples, Big Picture View of Course Material, Discrimination (i.e. classification), simple methods and Fisher Linear Discrimination, "sphering transformation" derivation)
Student Presentation 3/27/02 Trevor Park, Varimax rotation of PCA
Lecture 3/25/02 (Independent Component Analysis, toy examples, Curve Data examples & contrast with PCA, numerical issues and choice of "nonlinearity")
Student Presentation 3/13/02 LongYu, PCA and Smoothing
Lecture 3/11/02 (Independent Component Analysis, algorithm, non-Gaussianity, Q-Q plots, toy examples)
Lecture 3/06/02 (finishedSIZER background, started Independent Component Analysis)
Lecture 2/27/02 (SIZER background, which features are "really there"?)
Student Presentation 2/25/02 Hui-Bin Zhou, Shirnkage Estimation
Lecture 2/20/02 (PCA for boundary Fourier Corpora Collosa, intro and PCA for M-Rep Corpora Collosa, correlation PCA, PCA and clusters, mass flux data)
Lecture 2/18/02 (Dual Eigen Decompositions, statistics of PCA, intro to Corpora Collosa data with boundary Fourier representation)
Lecture 2/13/02 (Review of Linear Algebra, Singular Value and Eigen Decompositions, Multivariate Probability)
Lecture 2/11/02 (Elliptical Principal Component Analysis, Cornea Data, Another Toy Example, Start Deeper look at PCA, Review of Linear Algebra)
Lecture 2/6/02 (Robust, Spherical and Elliptical Principal Component Analysis)
Lecture 2/4/02 (Principal Component Analysis of Cornea Data, Introduction to Outliers and Robust Statistics)
Lecture 1/30/02 (Principal Component Analysis for curves, toy 3-d and 10-d examples, including Dog Legs, Fans, Parabolas, Gaussians and 2 clusters)
Lecture 1/28/02 (Introduction to Principal Component Analysis, careful 2-d example, intuition from curve view)
Lecture
1/21/02 (Introduction
to Functional Data Analysis, Data Representation, Object Space - Feature
Space duality, Main goals: "understanding population structure" & discrimination
(i.e. classification))
Link to Combined References
Course Meetings:
Time: Mon. - Wed. 8:40 - 9:55
Room: Rhodes 471
Course Web Site:
http://www.orie.cornell.edu/~marron/OR779NetworkData/OR779home.html
maybe easier to follow link from:
http://www.orie.cornell.edu/~marron/
Instructor: J.
S. (Steve) Marron
Office: Rhodes
234
Office Hours:
Mon. 10 - 11, Tuesday 11 - 12
Phone: (607)
255-9147
Email: marron@stat.unc.edu
Course Email List: please add yourself,
Subscribe to or778-sp02-l, by sending a message with the word subscribe in the Subject: field to the address: or778-sp02-l-request@orie.cornell.edu
To unsubscribe, send a message with the word unsubscribe in the Subject: field to or778-sp02-l-request@orie.cornell.edu
(useful for announcements, such as "notes now posted")
Recommended Textbook:
Ramsay, J. O. & Silverman,
B. W. (1997) Functional Data Analysis, Springer, N.Y.
Course Work / Grading
Based on a presentation
Presentations: can be any of (you choose, or I suggest):
- a section of Ramsay and Silverman
- a paper by others
-
your own work
Let's discuss soon