Universität Wien FIND

Due to the COVID-19 pandemic, changes to courses and exams may be necessary at short notice. Inform yourself about the current status on u:find and check your e-mails regularly.

Please read the information on https://studieren.univie.ac.at/en/info.

400025 SE Field Experiments (2021S)

SE Methods for Doctoral Candidates

Continuous assessment of course work


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


max. 15 participants
Language: English


Classes (iCal) - next class is marked with N

Monday 21.06. 09:45 - 11:15 Hörsaal 8 Oskar-Morgenstern-Platz 1 1.Stock
Monday 21.06. 13:15 - 15:45 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
Tuesday 22.06. 09:45 - 11:15 Hörsaal 8 Oskar-Morgenstern-Platz 1 1.Stock
Tuesday 22.06. 13:15 - 15:45 Hörsaal 5 Oskar-Morgenstern-Platz 1 Erdgeschoß
Wednesday 23.06. 09:45 - 11:15 Hörsaal 5 Oskar-Morgenstern-Platz 1 Erdgeschoß
Wednesday 23.06. 13:15 - 15:45 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
Thursday 24.06. 09:45 - 11:15 Hörsaal 8 Oskar-Morgenstern-Platz 1 1.Stock
Thursday 24.06. 13:15 - 15:45 Hörsaal 5 Oskar-Morgenstern-Platz 1 Erdgeschoß
Friday 25.06. 08:00 - 10:00 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
Friday 25.06. 13:15 - 15:15 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß
Friday 25.06. 16:30 - 17:30 Hörsaal 3 Oskar-Morgenstern-Platz 1 Erdgeschoß


Aims, contents and method of the course

Correlation is not causation. You must have heard this warning many times. But, what then is causation,
and how can we test causal hypotheses, and identify the effects of interventions in the real world? Building
on the potential outcomes framework, the module encourages students to think about challenges to causal
inference at the design stage of a study. Published work will be evaluated based on how it addresses three key assumptions underlying causal inference: independence, excludability, and non-interference. Field experiments are attractive because they enable the researcher to ground statistical and causal inferences in features of the research design rather than assumptions about the world. The goal of this 5-day course is to provide participants with the methodological knowledge and the practical skills to design, analyse, and eventually conduct their own field experiments. We will use the textbook by Gerber and Green (2012) as our main guide. Strong emphasis will be placed on developing practical skills for real research scenarios. Given resources, how should subjects be assigned to conditions? How many treatment arms should we include? How do we plan to analyze the resulting data? Each day will be broken up into a morning and an afternoon session. The morning session will provide a mix of statistical theory and practical tips for implementing field experiments, while the afternoon session will be dedicated to computer practice.

Assessment and permitted materials

Minimum requirements and assessment criteria

The pre-requisite is any course covering linear regression and hypothesis testing. Other than that, we will build the statistical foundations for randomized field experiments from the ground up. For those with a deeper statistical background, there will be opportunities for exploration of more advanced topics.

Learning Outcomes: Students will understand the potential outcomes framework, and the key assumptions underlying causal inference. They will also understand how to design, analyse and interpret randomized field experiments, and they will be aware of the specific challenges that field experimentalists face. Moreover, they will gain the practical skills of applying these insights about experimental design and statistical knowledge to experimental data.

Problem Sets: Students will complete two short practice problem sets in the evenings of days 2 and 4. The submission deadline is 9am the next morning, and I will provide feedback the following day.
Experimental Design: For the research design session on day 5, students will be asked to come prepared with
a 2-pager outlining an experimental design including
1 causal research question
2 hypotheses
3 experimental design
sample, experimental conditions, outcome variables, type of random assignment.

Course Page: There is a course dropbox to which all students will have access to.

Examination topics

Reading list

Required Textbook:
Gerber, Alan and Donald P. Green. Field Experiments: Design, Analysis, and Interpretation, New York: W.W.
Norton, 2012.

Recommended Texts on Field Experiments:
John, Peter. Field Experiments in Political Science and Public Policy: Practical Lessons in Design and Delivery,
Routledge, 2017.

Glennerster, Rachel and Kudzai Takavarasha. Running Randomized Evaluations: A Practical Guide, Princeton
University Press. 2013.

Karlan, Dean and Jacob Appel. Failing in the Field , Princeton University Press, 2016.

Software: Students will have a choice between using R or Stata. If you are unfamiliar with both languages, I
would suggest using R, as it is free and open source. All analyses that we will conduct are easily done in either
language, and code will be provided in both languages. However, demonstrations will focus on R.

R Intro:
Imai, Kosuke. Quantitative Social Science. An Introduction. Princeton: Princeton University Press, 2017.
Grolemund, Garrett and Hadley Wickham. Learn R Online with R for Data Science: https://r4ds.had.co.nz
Phillips, Nathaniel D. The Pirate's Guide to R: https://bookdown.org/ndphillips/YaRrr/
Lecture Outline
1. Introduction to the Potential Outcomes Framework
2. Sampling Variability and Randomization Inference
3. Analyze as you Randomize: Blocking, clustering and covariates
4. Dealing with complications (non-compliance and attrition)
5. Designing and Executing Field Experiments

Association in the course directory

Last modified: Mo 14.06.2021 15:49