s-news
[Top] [All Lists]

Live On line Spring Semester course on Bayesian/Computational Statistics

To: s-news@lists.biostat.wustl.edu
Subject: Live On line Spring Semester course on Bayesian/Computational Statistics using Splus/ R and WinBUGS
From: Ernst Linder <elinder@cisunix.unh.edu>
Date: Thu, 06 Jan 2005 14:48:22 -0500
References: <41372DA4.2000109@cisunix.unh.edu>
User-agent: Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.0.1) Gecko/20020823 Netscape/7.0
Greetings!

This course might be of interest to some members of this list.
Also please bring this to the attention of anyone who might benefit from
this course.

For additional information please feel free to contact:
elinder@cisunix.unh.edu

Ernst Linder.

***************************************************************************
Announcement:  Fully interactive "live - on - line" course on
Bayesian and Computational Statistics using S/R and WinBUGS
***************************************************************************

This course is offered as a regular 3 credit course by the
Department of Mathematics and Statistics,
University of New Hamphsire, USA.

Class Times:  Tuesdays and Thursdays 11:10 - 12:30  EST  (USA)
January 18 - May 10 2005, excluding semester break week March 14 - 18

You can access the course on any computer that is connected to
the internet.
Visit www.unh.edu/farview for details.

Tuition (Continuing Education non-NH resident rate): US $ 846
See  www.learn.unh.edu  for details about registration and payment.

The official course information is
MATH 979 01 22479 Top/Stat Bayesian & Comp Stats 3.0
T R 1110-1230 PM MUB DL E Linder





                     COURSE OUTLINE


In this course we will be discussing current approaches to Bayesian modeling / 
data
analysis, and computation in statistics and related science fields.  The course 
will
be introductory in the beginning but will advance fairly quickly to more 
current and
especially computationally sophisticated methods. The emphasis will be on 
methodological
development and practical applications.

Prerequisites:

1)  Knowledge of intermediate statistics:  Distributions, discrete and 
continuous random
variables, transformation of variables (calculus based!),  bivariate and 
multivariate
normal distribution.
2)  Working knowledge of linear regression and analysis of variance.
3)  Basic linear algebra: Vectors and matrices, linear spaces, matrix 
multiplication,
inverse of a matrix, positive definiteness.  Matrix-vector notation for linear 
regression
and ANOVA.

List of Topics

1.  Fundamentals of Bayesian Inference
2.  One parameter and Multi-parameter Models
3.  Large Sample Inference
4.  Some Fundamentals:  Bayesian Design, Model Checking, Sensitivity Analysis
5.  Regression Models
6.  Computational Methods: Gibbs Sampling, Markov Chain Monte Carlo (MCMC)
7.  Advanced Modeling 1: Hierarchical Linear Model, Variable Selection
8.  Advanced Modeling 2: Generalized Linear Model
9.  Advanced Modeling 3:  Multivariate Data, Time Series, Spatial and Spatial 
Temporal Data.
10. Missing Data, Imputation.


Course Organization

Text:   (Required):
"Bayesian Data Analysis"  by  A. Gelman, J. B. Carlin, H.S. Stern and D.B.Rubin.
(Chapman and Hall - CRC Press, second edition: 2004).
Visit the website for the book (by Andrew Gelman): 
http://www.stat.columbia.edu/~gelman/book/
It has, among other things, solutions to selected exercises with S (S-plus) 
code for
computations and graphs.

Software:       We will be using the following software
-  S-Plus Version 6.2.  (freely available to students through UNH’s site 
license).
-  R (freeware)  -  Winbugs  (freeware)

Distance Learning:  This course is offered as “FAR-VIEW” synchronously on-line 
using
LEARNLINC. LearnLinc is a client-server software tool being used as a platform 
for Distance
Education at the University of New Hampshire. With LearnLinc, students can 
attend a live
class session led by an instructor using their Windows computer system and an 
Internet
connection. The instructor's voice, along with course materials, are delivered 
to both
local and off-campus students in real time.
Learn more about FarView at www.unh.edu/farview

Homework:  Homework assignments will be given on a regular basis.  Most 
homeworks will
require computer-based calculations.  Occasionaly computer labs will be 
scheduled where
students can work on homework assignment with the help of the instructor.

Final Exam:  A comprehensive final take-home exam will be assigned during the 
last week of
classes.

Grade:  Homework 65 %,  Final Exam:  30 %,  Participation 5%.


--
****************************************************************
Ernst Linder                        elinder@math.unh.edu
Department of Mathematics and Statistics     603 - 862- 2687
University of New Hampshire            Fax:  603 - 862 - 4096
Durham, NH 03824                www.math.unh.edu/~elinder
****************************************************************


<Prev in Thread] Current Thread [Next in Thread>
  • Live On line Spring Semester course on Bayesian/Computational Statistics using Splus/ R and WinBUGS, Ernst Linder <=