“No causation without manipulation” (Holland 1986: 954). But what can be done to establish causal interpretation of quantitative data if an intervention or experiment is not possible or unethical? In this PhD course, students will learn about causal identification strategies and endogeneity in management research if natural experiments are not feasible. This course is suited to all PhD students who plan to pursue a quantitative research approach. The content of this course is highly relevant to PhD students from the departments of Global Business and Trade, Management, Marketing, and Strategy and Innovation. It is advisable but not necessarily prerequired that participants have already an idea about their research questions, the related theoretical concepts, and how these concepts could be tested empirically.

In summary, this course provides best practices for how to deal with endogeneity and other related topics in observational data.

After completion of this course, PhD students will be confident in applying various causal identification strategies and knowing their specific advantages and disadvantages.

In detail, participants will learn about

• Causal identification and endogeneity bias
• Instrumental variable approaches
• Sample selection issues (inverse Mills ratios)
• Gaussian copulas
• Propensity score matching
• Regression discontinuity
• Other related topics

Examination-immanent courses (PI) have compulsory attendance. In case of absence the lecturer must be informed in advance if possible. More detailed regulations on absenteeism will be explained in the first session.

This course combines lecturing with more interactive elements of student presentations and open discussions. Participants should read the three papers below for a common understanding of the topic prior to the introduction session. In the first session, the course instructor will give an overview of the different approaches and unique challenges related to testing for endogeneity. In the second highly interactive session, students will give a brief presentation of their PhD project and assess which identification strategy fits their research question(s) and empirical data. Alternatively, participants may present a paper of their choice from a top-tier journal and assess the applied identification strategy. Prior to the presentations, students will prepare and share their slides via upload to Learn@WU. After each presentation, the remaining participants will have the opportunity to give constructive feedback. The course instructor will spur and moderate a discussion that leads to a working plan for revising the chosen identification strategies. In the next two sessions, participants will be assisted to implement the different approaches in a software package such as R, Stata or Mplus with provided exemplary data or their own empirical data if already available. The fifth session will consist of a final essay summarizing the results for endogeneity testing on a new data set. A final discussion will assess the lessons learned.

Presentation of your PhD project (or a paper of your choice): 25%

Feedback to the other participants’ presentations: 25%

Participation: 25%

Final essay: 25%

Basic knowledge of statistics

Access to a software package (SPSS, R, Stata and/or Mplus)

Please log in with your WU account to use all functionalities of read!t. For off-campus access to our licensed electronic resources, remember to activate your VPN connection connection. In case you encounter any technical problems or have questions regarding read!t, please feel free to contact the library at readinglists@wu.ac.at.