• HLPMiniCourse

HLP Lab Mini Course on Regression Methods

May 27 2008 - June 12 2008

Texts

• [http://www.amazon.com/Analysis-Regression-Multilevel-Hierarchical-Models/dp/0521867061/ref=sr_1_1?ie=UTF8&s=books&qid=1211219851&sr=8-1 Data Analysis Using Regression and Multilevel/Hierarchical Models] by Gelman & Hill (2007). [http://www.stat.columbia.edu/~gelman/arm/ Online resources]. G&H07.

• [http://www.amazon.com/Analyzing-Linguistic-Data-Introduction-Statistics/dp/0521882591/ref=sr_1_1?ie=UTF8&s=books&qid=1211219948&sr=8-1 Analyzing Linguistic Data: A Practical Introduction to Statistics using R] by Harald Baayen (2008). [attachment:baayen_analyzing_08.pdf Complete electronic draft]. Baa08.

• [http://www.amazon.com/Introductory-Statistics-R-Peter-Dalgaard/dp/0387954759/ref=sr_1_1?ie=UTF8&s=books&qid=1211228905&sr=8-1 Introductory Statistics with R] by Peter Dalgaard (2004). [http://staff.pubhealth.ku.dk/~pd/ISwR.html Online resources]. Dal04.

• [http://www.amazon.com/Categorical-Analysis-Wiley-Probability-Statistics/dp/0471360937/ref=pd_bbs_1?ie=UTF8&s=books&qid=1211231537&sr=8-1 Categorical Data Analysis] by Alan Agresti (2002). [http://www.stat.ufl.edu/~aa/cda/cda.html Online resources]. Agr02.

R packages

• [http://cran.r-project.org/web/packages/Design/index.html Design]. Linear and generalized linear regression.

• [http://cran.r-project.org/web/packages/lme4/index.html lme4]. Multilevel modeling.

• [http://cran.r-project.org/web/packages/arm/index.html ARM]. Companion package for Gelman & Hill (2007).

• [http://cran.r-project.org/web/packages/languageR/index.html languageR]. Companion package for Baayen (2008).

How to read

One goal of this course is to make sure we're all comfortable with the same terminology and methods. Another goal is to make sure that as new people enter the community, we can bring them up to speed pretty quickly. To help with both of these goals, we're asking that you take some additional steps when you're doing the reading for this class.

1. Keep an eye out for redundancy. If multiple pieces of assigned reading cover the same topic, and you find a single one of the treatments to be superior and sufficient, please make a note describing the nature of the redundant content, which source you preferred, and why. This will help us develop a set of "canonical" readings on these topics.

2. Record and investigate unexplained or unclear terminology. Because we're cherry picking chapters from multiple sources, it's likely that at some point an author will use a term that was originally presented in some (unread by us) earlier section of the text. Alternatively, an author might just assume knowledge that we don't have. In any case, when you come across a term in the reading that you believe is not explained well enough, please make a note of the term and where you found it. Then, please go one step further. Do your best to find a simple definition of the term, and record it for others to use ([http://en.wikipedia.org/wiki/Statistics Wikipedia] and [http://mathworld.wolfram.com/topics/ProbabilityandStatistics.html MathWorld] are likely to be good resources for this, but also feel free to consult your favorite stats text books).

Session 5: Mixed logit models

Tuesday, June 10 2008.

Reading

* In this chapter, Gelman & Hill define some multilevel models in BUGS rather than in R. We will either provide translations for you, will do the translations together in class, or will assign the translations as an assignment.

Assignments

Session 6: Computational methods for model fitting

Thursday, June 12 2008.

Reading