Banner Viadrina

Cause and Effect - Advanced Methods

Exam number: 6100

Semester: from 4th semester (Schwerpunktbildung)

Duration of the module: One semester

Form of the module (i.e. obligatory, elective etc.): Elective

Frequency of module offer: Each summer semester

Prerequisites: Prerequesite: Cause and Effect - An Introduction
The combination "Cause of Effect - An Introduction" and "Cause and Effect - Advanced Methods" offers interested students a crash-course to obtain up-to-date knowledge about applied tools for uncovering causality using observational data.

Applicability of module for other study programmes:
Obligatory or elective in other study programmes. For further information check regulations of the study programme.

Person responsible for module: Prof. Dr. Felix Weinhardt

Name of the professor: Prof. Dr. Felix Weinhardt

Language of teaching: English

ECTS-Credits (based on the workload): 6

Workload and its composition (self-study, contact time):
Contact time (lecture, tutorials, seminar etc.) 60 h; self-study: 120 h

Contact hours (per week in semester): 4

Methods and duration of examination:
In normal times, this course is assessed by a final exam. In the summer semester 2021 this assessment will instead be based on take-home exercises that have to be completed and handed in (online, moodle) over the duration of the course. Further details will be communicated on the start of the course.

Emphasis of the grade for the final grade: Please check regulations of the study programme

Aim of the module (expected learning outcomes and competencies to be acquired):
The course will provide participants with an up-to date tool-kit of applied econometrics to answer causal questions. Participants will impment the learnt methods using Stata using a series of practical exercises. The skills learnt in this course will be useful for any applied work (i.e. Bachelor-thesis) but hopefully also result in a "shift in perspective" with respect to causal claims that are made elsewhere in everyday-life. More details can be found on the moodle webpage.
The aim of the course is to change students' perceptions of the world and causal claims that are made by others around us every single day. To do this, the course will introduce students to the quantitative evaluation of policies or interventions using regression based evaluation methods. In order to build the required intuition and tools, the first section of the course will provide students with a short primer in regression analysis, including a short introduction to Stata. We will then subsequently discuss various strategies to potentially overcome omitted variable biases and other forms of endogeneity, with a particular focus on panel data econometrics. Throughout, the focus of the course will rest on identifying strategies that allow for causal interpretation rather than mathematical deriva-tions of theoretical results. Econometric challenges will always be discussed in close reference to real-world questions and the relevant literature.

Contents of the module:
Advanced methods for detecting causal effects. Topics will vary depending on new developments in the field, but likely include:
- potential outcomes framework
- instrumental variables estimation and complier analysis
- difference in differences estimation
- matching and synthetic controls
- regression discontinuity (sharp and fuzzy)
- quantifying bias, assumptions about unobservables
- anaysis of experimental data
- non-standard standard errors and experimental inference

Teaching and learning methods:
Lectures and hands-on seminars, integrated

Special features (e.g. percentage of online-work, practice, guest speaker, etc.):
Lectures and material will be delivered online, mostly via moodle and video clips, with on-site seminar sessions in the computer lab, if possible. Students are expected to work on take-home exercises throughout, and to present and discuss their results in the (online-) seminars.

Literature (compulsory reading, recommended literature):
Angrist and Pischke: Mastering Metrics
Scott Cunningham: Mixedtape
Angrist and Pischke: Mostly Harmless Econometrics

Further information:
Registration in Moodle Viadrina required.