Stat 687

Instructor: Rebecka Jornsten , Email: rebecka@stat.rutgers.EDU

Lecture: Thursday 12noon-2pm, 552 Hill

Office Hours: Per appointment with the individual instructor: Rebecka Jornsten, Regina Liu, Bill Strawderman, David Tyler, Cunhui Zhang.

[ About the course | Links | Suggested papers | Schedule]

Announcements

About the course:

Course requirements
In this course you will practise your presentation skills, both verbal and in writing. The first task is to summarize and review a topic assigned to you. You will summarize and present at least one paper on the topic in a 30 minute in-class presentation, and write a 3-5 page report on the paper/topic. Your fellow students, and the co-instructors will present you with a set of questions after the presentation.

Your second task consists of following up on the first topic presentation: conduct a literature review, and present a summary (40 minutes) to your fellow students and the co-instructors. Make sure to address the questions raised after the first presentation. You are also required to summarize the topic with a 10 page final report.

Note, all students are required to read all topic primary papers, and have to contribute to the topic discussion in an active manner. After each student presentation, you are required to submit a set of discussion questions in writing.

Grading
Your letter grade for the course will be based on the overall score you get from (1) the primary presentation and written component (3-5 pages), (2) the in-class contribution (active dicussant, and contributed questions), (3) the final literature review and presentation, and the final report (10 pages).

Links:

Course outline and sample report

Course outline and sample report - latex file

Some suggestions for how to organize your presentation

template for a presentation - a latex file. this requires that you install the beamer package.

Presentation Myths Richard A. Becker; Sallie Keller-McNulty The American Statistician, Vol. 50, No. 2. (May, 1996), pp. 112-115.

Suggested papers:

Topic I: Bagging

Leo Breiman, Bagging Predictors

Peter Buhlmann, Bin Yu, Analyzing Bagging.

Topic II: Cox regression model D.R. Cox, Regression models and life tables.

Topic III: The EM-algorithm

A.P. Dempster, N.M. Laird and D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm

X.L. Meng and D.A. van Dyk, The EM algorithm - an old fold song sung to a fast new tune

Topic IV: Extreme value theory: L. de Haan and J. de Ronde. Sea and wind, multivariate extremes at work.

Topic V: Emperical Bayes

H. Robbins. An empirical Bayes approach to statistics

C. Stein. Estimation of the mean of a multivariate normal distribution.

J. Berger. Minimax estimation of location vectors for a wide class of densities.

G. Casella, W. Strawderman. Estimating a bounded normal mean.

Improving on standard estimators in discrete exponential families, with applications to Poisson and NB distributions.

Topic VI: Dimension reduction.

P.J. Huber, Projection pursuit.

A. Hyvrinene, E. Oja, ICA: a tutorial.

A. Hyvrinene, Survey on ICA

Topic VII: Smoothing. C.K. Chu, I.K. Glad, F. Godtliebsen, J.S. Marron. Edge-preserving smoothers for image processing.

Topic VIII: Power-1 test H. Robbins. Statistical methods related to the law of the iterated logarithm.

Schedule:

The 1st set of presentations are schedules for Feb 1st and slide will be posted here.

Back to : Rebecka Jornsten

01/16/07