Autumn Semester 2020 takes place in a mixed form of online and classroom teaching.
Please read the published information on the individual courses carefully.

851-0252-19L  Applied Generalized Linear Models

SemesterSpring Semester 2020
LecturersV. Amati
Periodicitynon-recurring course
Language of instructionEnglish


AbstractGeneralized linear models are a class of models for the analysis of multivariate datasets. This class subsumes linear models for quantitative response, binomial models for binary response, loglinear models for categorical data, Poisson models for count data. Models are presented and practiced from a problem oriented perspective using applications from the social, economic and behavioural sciences.
ObjectiveThe aim of this course is to acquire knowledge about generalized linear models and a practical understanding of how to apply these models. Further objectives for the course participants are to be able to choose the most suitable methods to analyse multidimensional datasets, to perform the analysis using the statistical software R, and to critically assess the results obtained.
ContentThe following topics will be covered:

* Introduction to generalized linear models
* The general linear model: ANOVA and ANCOVA
* Models for binary outcomes: logistic regression and probit models
* Models for nominal outcomes: multinomial logistic regression and related models
* Models for ordinal outcomes: ordered logistic regression and probit models
* Models for count outcomes: Poisson and negative binomial models
Lecture notesLecture notes are distributed via the associated course moodle.
Literature* Long, J. Scott. (1997). Regression models for categorical and limited dependent variables. Thousand Oaks, Calif: Sage Publications.
* Hosmer, David W, Lemeshow, Stanley, & Sturdivant, Rodney X. (2013). Applied logistic regression. Hoboken: Wiley.
* Fox, John. (2016). Applied regression analysis and generalized linear models (Third ed.). Los Angeles: SAGE.
* Fox, John, & Weisberg, Sanford. (2019). An R companion to applied regression (Third ed.). Los Angeles: SAGE.
Prerequisites / NoticeA sound understanding of estimation methods, hypothesis testing and linear regression models (OLS) is required