Universität Wien

230107 UE EC: Modelling choices - Regression models for binary and categorical outcomes (2023S)

3.00 ECTS (1.00 SWS), SPL 23 - Soziologie
Continuous assessment of course work
Moodle

Registration/Deregistration

Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).

Details

max. 28 participants
Language: English

Lecturers

Classes (iCal) - next class is marked with N

Monday 06.03. 10:00 - 14:00 PC-Raum 1 Schenkenstraße 8-10, 1.UG
Tuesday 14.03. 11:30 - 15:30 PC-Raum 1 Schenkenstraße 8-10, 1.UG
Monday 20.03. 10:00 - 14:00 PC-Raum 1 Schenkenstraße 8-10, 1.UG

Information

Aims, contents and method of the course

This course will provide participants with the detailed understanding and advanced skills needed to interpret the results of logistic regression models with binary, ordinal and multinomial outcome variables.

Many courses on statistical methods only briefly cover how to interpret the results of logistic regression models. However, the results of such models are more difficult to interpret and to present than those for OLS regression models. In particular, interpreting logistic regression results is not limited to looking at coefficients and standard errors: we need to go beyond the simple regression output to gain a full understanding of what our results mean. This course will provide researchers with the tools to make the most of their regression results and to present their results in the most effective way possible. The focus throughout this course will be on practical analysis rather than on statistical theory.

In the first sessions, we will begin with a review of binary logistic regression models. What is the statistical rationale for these models, and how do they differ from OLS models? This session will also provide a review of basic commands for Stata, with a particular focus on running binary logistic regression models. Then, we will consider the two easiest ways of interpreting the results of binary logistic regressions. We will discuss how to interpret regression coefficients and then move on to using the odds ratios interpretation of the results. After that, we will move on to interpreting binary logistic regression results using predicted probabilities. We will learn how to calculate predicted probabilities by hand. We will then cover the various ways in which Stata can help in the calculation of predicted probabilities.

In the second half, we will learn how to present regression results and predicted probabilities graphically. Advantages and disadvantages of presenting results using predicted probabilities will be discussed. We will then consider the importance of uncertainty and how this can be included in the presentation of predicted probabilities. We will learn how to use Stata to run simulations. Finally, we will consider the level at which we should set other variables when calculating predicted probabilities. We will also consider other topics related to the interpretation of logistic regression models. The focus will lie on diagnostic techniques and on measures of model fit.

We will also consider how to interpret interaction effects in (binary) logistic regression models as well as other discrete outcomes (ordinal and nominal variables). Here, results need to be presented particularly clearly and carefully for readers to understand results well.

This course is at an intermediate level, so some familiarity with OLS regression will be assumed.

By the end of this course, participants will be able to:
- interpret the results of binary, ordinal and multinomial logistic regression models using log odds, odds ratios and predicted probabilities,
- present these results as tables and graphs in ways suitable for general and specialist audiences,
- interpret interaction effects in the appropriate ways,
- distinguish different measures of model fit and include these in presentations of results,
- run straightforward diagnostic tests of their model,
- and use Stata to run and understand logistic regression models.

Assessment and permitted materials

The format of classes will be informal. Lectures will be short, and the focus of classes will be computer exercises and classroom discussions of results and homework. Lectures will take up at most a third of the overall classroom time as the focus in this class is on practical analysis. Students are encouraged to bring along their own data and research questions.

Important Grading Information:
The provision of all partial tasks is a prerequisite for a positive assessment, if not explicitly noted otherwise.
All students who received a place in the course are assessed if they have not deregistered from the course in due time or if they have not credibly shown an important reason for their failure to deregister after the cause for this reason does no longer apply
Students who credibly show an important reason (e.g. a longer illness) for the withdrawal from a course with continuous assessment are not assessed.
Whether this exception applies is decided by the lecturer. The request for deregistration must be submitted immediately.

If any requirement of the course has been fulfilled by fraudulent means, be it for example by cheating at an exam, plagiarizing parts of a written assignment or by faking signatures on an attendance sheet, the student's participation in the course will be discontinued, the entire course will be graded as "not assessed" and recorded accordingly.
You can find these and other provisions in the study law: https://satzung.univie.ac.at/studienrecht/.

In case you have received three negative assessments of a continuously assessed course and want to register for a fourth attempt, please make sure to contact the StudiesServiceUnit Sociology. (for more information see "third attempt for continuously assessed courses" https://soziologie.univie.ac.at/info/pruefungen/#c56313)

The plagiarism-detection service (Turnitin in Moodle) can be used in course of the grading.

Minimum requirements and assessment criteria

There will be two homework assignments (30 % each) as well as a final assignment (30 %) that will help participants to gain further understanding and experience in interpreting binary logistic regression models. Participation will account for 10% of the grade. Attendance at all classes is compulsory, though half of one class can be missed.

Examination topics

see above

Reading list

Orme, John G. and Terri Combs-Orme (2009) Multiple Regression with Discrete Dependent Variables, Oxford University Press: Oxford.

Long, J. Scott (1997) Regression Models for Categorical and Limited Dependent Variables, Sage: Thousand Oaks.

Long, J. Scott and Jeremy Freese (2006) Regression Models for Categorical and Dependent Variables using Stata, 2nd edition, Stata Press: College Station.

Menard, Scott (2001) Applied Logistic Regression Analysis, 2nd edition, Sage: London.

Pampel, Fred C. (2000) Logistic Regression: A Primer, Sage: London

Association in the course directory

Last modified: Tu 21.02.2023 18:49