ST 740-001:
Bayesian Inference and Analysis
Fall Session, 2018

Detailed Course Syllabus



Course:

ST 740-001 Bayesian Inference and Analysis

Time:

1:30pm -- 2:45pm: Mondays & Wednesdays

Place:

2102 SAS Hall

.

.

Instructor:

Sujit K. Ghosh

Email:

sujit.ghosh@ncsu.edu

Telephone

919-515-2570

Office:

5116 SAS Hall (5th floor)

Office hours:

3:00pm -- 5:00pm: Mondays (or by appointment)

. .

Teaching Assistant:

Suman Majumdar

Email:

smajumd2@ncsu.edu

Office:

1101 SAS Hall (Statistics Tutorial Center)

Office hours:

3:00pm -- 5:00pm: Tuesdays (tentative)


Class links: Course materials| Private Tutors

Course prequisite: ST 702

Optional texts:
Hoff, Peter A (2009). First Course in Bayesian Statistical Methods, Springer Texts in Statistics (ISBN: 978-0-387-92299-7)
Robert, Christian P.(2007). The Bayesian Choice, 2nd Edition. Springer Texts in Statistics (ISBN: 0-387-95231-4)
Robert, Christian P. and Casella, George (2005). Monte Carlo Statistical Methods, Second Edition, Springer Texts in Statistics (978-1-4419-1939-7)

Grades: It is the student's responsibility to be aware of their grades in the course and the appropriate level of work required. Your final grade in this course will depend on the following:
Item
Portion of Grade
Homework (Assigned roughly weekly)
15% of grade (lowest two scores dropped)
Midterm Exam I (Oct 3rd, 2018, 1:30-2:45)
30% of grade
Midterm Exam II (Nov 7th, 2018, 5:00PM, ET)
30% of grade
Final Exam/Project (Dec 3rd, 2018, 5:00PM, ET)
25% of grade
The course uses the standard NCSU grading scale.

Incomplete (IN) grades are given only as specified in university regulations. Students who wish to audit the course with satisfactory status must register officially for the course and will be required to obtain an 75% or greater on the homework assignments to receive credit. There is no requirement to take the midterm exams or do the final project.

Homework: There will about 10 homework assignments during the semester with the lowest two assignment scores being dropped. Many of the assignments will include a programming portion that will require the use of R and so students are highly encouraged to explore Bayesian inference using R (OpenBUGS). As the lowest two scores are dropped, no late assignments are accepted.

Midterm Exams: First midterm exams is closed book and closed notes. while the second midterm exam will require programing and will need to be submitted electronically by email. All exams are cumulative. Students who are unable to take an exam for a legitimate unavoidable reason may take a make-up exam only if the student provides suitable documentation of the delay (at least two days prior to the scheduled exam day) and they are able to take the make-up in a very timely manner. If a make-up exam can't be taken, one of the midterm exams will be reweighted for the missing midterm exam. Students are required to take at least one of the two midterm exams otherwise a grade of F will be assigned.

Final Project: Toward the end of the semester, there will be a larger final project done in small groups. Each group will be required to submit a title and abstract of the proposed project. Once the project is approved by the instructor, each group will make a seminar style presentation and submit a written report. Details will be provided as the project nears.

Students with disabilities: Reasonable accommodations will be made for students with verifiable disabilities. Any student who feels they may need an accommodation based on the impact of a disability should contact the instructor privately to discuss your specific needs. In order to take advantage of available accommodations, students must register with Disability Services for Students at 1900 Student Health Center, Campus Box 7509, 515-7653. For more information on NC State's policy on working with students with disabilities, please click here

Academic Misconduct: Cheating, plagiarism and other forms of academic dishonesty will not be tolerated. To create a fair and equitable environment, the instructor aggressively enforces the universities policies on academic misconduct. All exams are to be completed individually. Although working together on written assignments to overcome obstacles is encouraged, each student must compose and write their own answers, explanations, analyses, and reports unless otherwise specified. All cases of academic misconduct will be handled as set out in university policies. For additional information see: Student Conduct Policies
Course goals: The course provides an introduction to Bayesian inference; specifying prior distributions; conjugate priors, summarizing posterior information, predictive distributions, hierachical models, asymptotic consistency and asymptotic normality. Markov Chain Monte Carlo (MCMC) methods and the use of existing software (e.g., WinBUGS, JAGS using R). Content: Prior distributions; Objective Bayes priors; Bayes rules; Gibbs sampling; Metropolis-Hastings sampling; Bayes factors; Semiparametric Bayesian methods; Model diagnostics.

Course Outline:
Basics of Bayesian inference
Computational Tools for Bayesian Analysis
Models for Independently Observed Data
Models for Dependent Onservations
Models with Infinite Dimensional Parameters

Calendar of Events:
8/22/18 (Wednesday: First day of classes
8/28/18 (Tuesday): Last day to add a course without permission
09/03/18 (Monday): Labor day (no class)
10/03/18 (Monday): Midterm Exam I
10/19/18 (Friday): Drop/Revision deadline
10/31/18 (Wednesday): Project Proposal Due
11/07/18 (Monday): Midterm Exam II
12/03/18 (Monday): Final Project due
12/05/18 (Wednesday): Last day of classes
12/14/18: No in-class Final exam

Communication: Students are expected to check their NCSU email regularly. Students who do not use their NCSU email should arrange to have this email forwarded to an account they do use. Due to university regulations the instructor can send course announcements only to NCSU email addresses.

Online Class Evaluation: Online class evaluations will be available for students to complete during the last two weeks of class (November 20 - December 1). All evaluations are confidential; instructors will never know how any one student responded to any question, and students will never know the ratings for any particular instructors.
Click ClassEval for further information.

Last updated on: August 16, 2018