Syllabus

Data analyses and inferential techniques applied to data described by stochastic processes. Inferential techniques for Markov models, Poisson processes, point processes, birth/death processes, and cluster processes. Techniques for inference applied to both stationary and nonstationary processes. Relationships between deterministic partial differential equation models and stochastic models. Modeling applications in time series, spatial analyses, genetics, epidemiology, text mining, and other application areas.

All models are wrong, but some are useful

-G. E. P. Box

Grading policies, office hours, and general information

---

Course Objectives

The intent of the course is to learn how to:

• Develop and deploy stochastic models for complex data structures.
• Implement inferential simulation techniques for classical, likelihood, and Bayesian models.
• Explain the relationships between deterministic models, based on differential equations, and their stochastic counterparts.
• Apply the various methods to complex real world modeling problems.
• Compare and evaluate each method based on accuracy and efficiency.

Logistics

• Lecture Times and Location:  Tues., Thurs. 9:30 - 10:45 PM,  in Hutcheson 207.
• Instructor: Professor Scotland Leman,   410 Hutcheson Building,   ,   leman(AT)vt(DOT)edu
• Instructor's Office Hours:   (TBA)
• Teaching Assistants:    TBA
  
• TAs' Office Hours:  (TBA)
  

Prerequisites

Students must have completed graduate level inference, have extensive knowledge of Bayesian models (STAT 5444), and understand the basics of MCMC (STAT 5304).

Readings

There is no textbook for this class. We will have weekly reading assignments which will come from high level research journals. Recommended text books follow as:

Daphne Koller, Nir Friedman Probabilistic Graphical Models: Principles and Techniques  (Adaptive Computation and Machine Learning series)

This book covers a wide spectrum. Lots of attention is paid to Markov Random Fields and such, which will encompass a large portion of this class..

Sudipto Banerjee, Alan E. Gelfand, Bradley P. Carli Hierarchical Modeling and Analysis for Spatial Data  Chapman and Hall

This book is a good reference for the spatial statistics portion of the course.

Pole, West, and Harrison Applied Bayesian Forecasting and Time Series Analysis   Chapman and Hall

This book is a good reference for the time series portion of the course.

Computing

For computing, you may use any upper level language of your choosing. For instance, C/C++, Java, Matlab, R, all make for reasonable choices. This course will not levy a large computational burden, however, be prepared for some computational exercises.

Graded work

Graded work for the course will consist of quizzes, small homework exercises, presentations, and your final project. Your final grade will be determined as follows: (This is tentative)

Quizes	20 %
Homeworks	20 %
Presentations	10 %
Final Prject	50 %

There are no make-ups for exams, in-class or homework problems except for a medical or familial emergency or previous approval of the instructor.  See the instructor in advance of relevant due dates to discuss possible alternatives.

Cumulative numerical averages of 90 - 100 are guaranteed at least an A-.   Cumulative numerical averages of 80 - 89 are guaranteed at least a B-.   Cumulative numerical averages of 70 - 79 are guaranteed at least a C-.   Cumulative numerical averages of 60 - 69 are guaranteed at least a D-.  These ranges may be lowered, but they will not be raised (e.g., if everyone has averages in the 90s, everyone gets at least an A-).

Final Project

Your final project will determine the majority of your grade. The expectation is that you will write a journal quality paper using the topics described in the course.

Use the following structure to organize your paper:
1. Write a First Draft
2. Every essay or paper is made up of three parts:

introduction

body

conclusion

3. The introduction is the first paragraph of the paper. It often begins with a general statement about the topic and ends with a more specific statement of the main idea of your paper. The purpose of the introduction is to:

let the reader know what the topic is

inform the reader about your point of view

arouse the reader's curiosity so that he or she will want to read about your topic

4.The body of the paper follows the introduction. It consists of a number of paragraphs in which you develop your ideas in detail.

Limit each paragraph to one main idea. (Don't try to talk about more than one idea per paragraph.)

Prove your points continually by using specific examples and quotations from your note cards.

Use transition words to ensure a smooth flow of ideas from paragraph to paragraph.

5.The conclusion is the last paragraph of the paper. Its purpose is to

summarize your points, leaving out specific examples

restate the main idea of the paper

Your paper will be a technical manuscript that introduces a problem in stochastic modeling, inference, and/or computing, with a novel solution. The goal is to produce publishable research.

Academic honesty

You are expected to abide by Virginia Tech's Community Standard for all work for this course.  Violations of the Standard will result in a failing final grade for this course and will be reported to the Dean of Students for adjudication.  Ignorance of what constitutes academic dishonesty is not a justifiable excuse for violations.

For the homework problems, you may work with a study group with others but must submit your own answers, unless otherwise indicated.  For exams, you are required to work alone and for only the specified time period.     

Procedures if you suspect your work has been graded incorrectly

Every effort will be made to mark your work accurately.    You should be credited with all the points you've worked hard to earn!   However, sometimes grading mistakes happen.  If you believe that an error has been made on an in-class problem or exam, return the paper to the instructor immediately, stating your claim in writing.

The following claims will be considered for re-grading:

(i)    points are not totaled correctly;
(ii)   the grader did not see a correct answer that is on your paper;
(iii)  your answer is the same as the correct answer, but in a different form (e.g., you wrote a correct answer as 1/3 and the grader was looking for .333);
(iv)  your answer to a free response question is essentially correct but stated slightly differently than the grader's interpretation.

The following claims will not be considered for re-grading:

(v)   arguments about the number of points lost;
(vi)  arguments about question wording.

Considering re-grades takes up valuable time and resources that TAs and the instructor would rather spend helping you understand material.  Please be considerate and only bring claims of type (i), (ii), (iii), or (iv) to our attention.