Contents
2. Linear Models for Continuous Data
2.2. Estimation of the Parameters
2.3. Tests of Hypotheses
2.4. Simple Linear Regression
2.5. Multiple Linear Regression
2.6. OneWay Analysis of Variance
2.7. TwoWay Analysis of Variance
2.8. Analysis of Covariance Models
2.9. Regression Diagnostics
2.10. Transforming the Data
3. Logit Models for Binary Data
3.2. Estimation and Hypothesis Testing
3.3. The Comparison of Two Groups
3.4. The Comparison of Several Groups
3.5. Models With Two Predictors
3.6. Multifactor Models: Model Selection
3.7. Other Choices of Link
3.8. Regression Diagnostics for Binary Data
4. Poisson Models for Count Data
4.2. Estimation and Testing
4.3. A Model for Heteroscedastic Counts
5. LogLinear Models for Contingency Tables
6. Multinomial Response Models
6.2. The Multinomial Logit Model
6.3. The Conditional Logit Model
6.4. The Hierarchical Logit Model
6.5. Models for Ordinal Response Data
7.2. Censoring and The Likelihood Function
7.3. Approaches to Survival Modeling
7.4. The PieceWise Exponential Model
7.5. Infant and Child Mortality in Colombia
7.6. Discrete Time Models
Browsing or Printing?
The notes are offered in two formats: HTML and PDF, see the discussion below for more details.
I expect most of you will want to print the notes, in which case you can use the links below to access the PDF file for each chapter:
If you are browsing you can use the links in the tab strip above to go to the start of each chapter, or use the table of contents on the right to go directly to a specific section.
No, there is no Chapter 1 ... yet. One day I will write an introduction to the course and that will be Chapter 1.
* The list above has two extensions to the original notes: an addendum on Modeling OverDispersed Count Data, which describes models with extraPoisson variation and negative binomial regression, and a brief discussion of models for longitudinal and clustered data.
Suggested Citation
Rodríguez, G. (2007). Lecture Notes on Generalized Linear Models. Available at http://data.princeton.edu/wws509/notes/
The Choice of Formats
It turns out that making the lecture notes available on the web was a bit of a challenge, because the web browsers in current use were designed to render text and graphs but not equations. After looking at a number of options, I decided to offer the notes in two formats: HTML and PDF.

HTML is ideal for browsing the notes. The equations are rendered as well as possible using standard text rather than graphics. The resulting documents are more compact and can be viewed faster than alternatives that rely heavily on graphs, but the equations are not always as pretty as one might wish.

PDF is best for printing the notes. The layout is very close to the original but the files are bulkier and lack hyperlinks. To view this version you need a helper application or plugin called Acrobat, which can be downloaded from Adobe. There is a separate file for each chapter. Our PDF files are now smaller and look better on the screen!
Each format has its advantages but none is perfect. Hopefully a better solution will be available once MathML becomes standard. For more information see the references below.
Errata
If you find an error in the notes please let me know. Make sure you note the section (e.g. 2.1.7) or page, and as much detail as you can. I will keep an uptodate list of corrections online.
References
The notes were prepared using LaTeX, which produces PostScript or PDF. I generated the HTML pages from the original LaTeX source using a program called TtH written by Ian Hutchinson. I found the output from this program better than alternatives such as LaTeX2Html.
If you are interested in the problem of publishing mathematics on the Web you may want to visit the W3C Mathematics page, which describes MathML and provides a number of useful links. You may also want to read Ian Hutchinson's views, including comments and links to reviews of various approaches.
Continue with 2. Linear Models for Continuous Data