Course Home | Calendar | Data | Computing | SECC| BlackBoard | DSS Home | Duke Home

Instructor: Merlise Clyde
Office: 223 E Old Chemistry Building	Office hours: Mon/Wed 2:30 - 4:00 or by appointment
Phone: 681-8440	Email: clyde@stat.duke.edu
Lecture:: Monday Wednesday 1:15 - 2:30 Soc/Psych 126

TAs: Francesca Petralia and Minghui Shi
	Office hours: See the SECC schedule for times; location 211A/B Old Chemistry Building
	Email: Francesca Petralis <fp12@stat.duke.edu> and Minghui Shi <ms193@stat.duke.edu> You may also contact the TAs using the Communication Links on the Blackboard Site.

The course covers statistical thought and practice through indepth examination of a wide variety of problems. Emphasis is on data collection and management, sampling and design, and exploratory and graphical data analysis. Introduction to Bayesian statistical methods. Computer orientation is provided, with attention toward statistical packages (primarily R and WinBugs) and use of LaTeX, emacs and some Unix tools.

Topics will be selected from:

• data types, data manipulation and analysis, including data sets from a variety of application fields -- see the datasets link
• exploratory data analysis and statistical graphics
• elements of statistical inference using probability models, including basic issues of sampling-theory and Bayesian inference
• models for normal data including ANOVA and regression models
• models for binary and count/categorical data
• introduction to hierarchical models
• introduction to statistical programming environments such as R
• elements of simulation and introduction to Gibbs sampling using R and WinBugs
  

Though the course does not include rigourous development of statistical theory and methods, we will use and review various concepts and methods of inference, so that some familiarity with basic statistics is desirable. This is not intended as a "first course" in statistics. While familiarity with Bayesian methods is not a prerequisite, we will assume that students have frequentists perspective. Co-registration in STA 213 or recent experience with a similar class in mathematical statistics is expected.

Texts:

AFirst Course in Bayesian Statistical Methods: (required) by Peter Hoff

Bayesian Computation with R, by Jim Albert is also recommended.

An Introduction to R (required) by W.N. Venables, D.M. Smith and the R Development Core Team download PDF file

 

Students may find the following list of texts and references useful.

Grading:

The course grade will be based on homework (approximately weekly) and a midterm exam, data analysis project, and final exam.