P533/P534 Bayesian Data Analysis I & II, Prof. Kruschke

Introduction to Bayesian Data Analysis

Spring 2013: Mondays and Wednesdays, 10:10am-12:40pm,
Room 111 of the Psychology Building.

P533 and P534 are consecutive 8-week courses in one semester.
P533 is required for P534.
P533 is Section 26030, P534 is Section 22368.

Prof. John K. Kruschke

Success increasing with knowledge of Bayesian data analysis
Figure 1. Why you should enroll.
(Notice that the Bayesian analysis reveals many credible regression lines, for which the slopes and intercepts trade off, instead of just one "best" line.)

P533/P534 is a tutorial introduction to doing Bayesian statistics for data analysis. The course is intended to make advanced Bayesian methods genuinely accessible to real graduate students, and even unreal undergraduates (see pre-req's below). Many complete computer programs are provided for you do adapt to your own research.
• In P533, we start from the basics of probabilities and Bayes' theorem, and gradually work our way through contemporary Monte Carlo methods in the context of simple analyses, building up to simple linear regression and Bayesian versions of single-factor analysis of variance (ANOVA).
• In P534, we contrast null hypothesis significance testing with Bayesian approaches to null value assessment, as well as Bayesian approaches to power. Then we do a variety of more complicated realistic applications, covering the Bayesian versions of multiple linear regression, logistic regression, analysis of variance, etc., including a look at repeated-measures designs.
• The order of topics (as just described) is different from previous years, so that students who can only enroll in P533 (without continuing into P534) nevertheless learn about basic applications such as simple linear regression and single-factor ANOVA. More details about the schedule are provided in tabular form below, in the context of chapters from the course textbook.

Why go Bayesian? See Figure 1, above. But beyond that, sciences from astronomy to zoology are changing from 20th-century null-hypothesis significance testing to Bayesian data analysis, because Bayesian analysis provides rich information with flexible application to numerous models. Read more:  *Your click on this link constitutes your request to the author for a personal copy of the article exclusively for individual research, and the author's delivery of that copy. Any other use is prohibited.

Prerequisites:

  • This is not a mathematical statistics course, but some math is unavoidable. If you can handle basic summation notation like Σi xi and integral notation like ∫ x dx, you're in good shape. You will not need to generate mathematical derivations.
  • We will be doing a lot of computer programming in a language called R. R is free and can be installed on any computer. (The programs have graphics commands that are best suited for the Windows operating system. MacOS or Linux users can make small changes to the programs.) The road to understanding will be much smoother if you have already had some programming experience, in any language. It's easy to learn basic programming, but it can be time consuming, so if you don't have any previous experience, just anticipate spending more time. Learning to program can have huge payoffs in multiple situations later in your career, so it's worth the effort.
  • A previous course in traditional statistics (such as K300) or probability can be helpful as background, but is not essential. P533 and P534 proceed independently of traditional ("null hypothesis significance testing") statistical methods.

    Book cover. Textbook: Doing Bayesian Data Analysis: A Tutorial with R and BUGS, by J. K. Kruschke. Academic Press, 2011.

    Schedule
    Week of semesterCourseBook Chapters
    1P533Ch. 1, 2, 3: Intro; probability; R
    2P533Ch. 4: Bayes' rule
    3P533Ch. 5, 6: Beta distribution
    4P533Ch. 7, 8: Markov chain Monte Carlo (excluding 7.3.3 and 7.4.3)
    5P533Ch. 9: Hierarchical models
    6P533Ch. 14: Generalized linear model
    Ch. 15: Normal distribution.
    7P533Ch. 16: Linear regression
    8P533Ch. 18: Oneway ANOVA
    Ch. 23: How to report an analysis
    9P534Ch. 10: Model comparison (including 7.3.3 and 7.4.3)
    10P534Ch. 11: Null hypothesis significance testing
    Ch. 12: Bayesian approaches to null value assessment
    11P534Ch. 13: Power
    12P534Ch. 17: Multiple linear regression
    13P534Ch. 20: Logistic regression
    Ch. 21: Ordinal regression
    14P534Ch. 19: Two factor ANOVA
    15P534Ch. 22: Contingency table analysis

    Discussion: Please discuss the assignments and lectures on Oncourse under the "Forums" link. If you are attending the class but cannot get access to the Oncourse page, please e-mail Prof. Kruschke.

    Grading; Homework; Exams: There are homework exercises assigned every week or so. No exams or projects. Grades will be determined by performance on the homework assignments. All assignments are mandatory. There will be penalties for late homework unless you have a cogent excuse. These penalties are designed as an incentive to you because the material is cumulative; the penalties also help keep things fair to all students. If you must be late with an assignment, please notify the professor immediately.

    How does this course (P533/P534) differ from S626? The Dept. of Statistics offers S626, Bayesian theory and data analysis. S626 has a prerequisite of "two statistics courses at the graduate level", and provides a mathematical treatment of Bayesian data analysis. Students are encouraged to consider S626 after taking P533/P534.

    Disclaimer: All the information here is subject to change. Changes will announced in class.

    This web page is at URL = http://www.indiana.edu/~jkkteach/P533/