Development economics seminar, focused on designing and executing empirical projects with secondary survey data, with emphasis on DHS. During the first weeks, the instructors provide tools and examples. Later weeks center on student projects.

Topics:

• Research questions and study design

• Using secondary data: DHS structure, sampling, weights, ...

• Measurement: constructing indices, poverty, and health measures

• Causal identification with observational data

• Descriptive and exploratory analysis: heterogeneity, visualization, mapping

• Reproducible workflow: data management, code style, version control

• Presentation and scholarly writing

Working mode:

• Students work individually or in pairs. A short paper presentation is expected early in the semester. The final presentation of one's own work and papers (i.e. extended research proposals) are due at the end. Proposals can be causal analyses or simple correlational descriptives.

• Formulate a clear, policy-relevant research question grounded in development economics.
• Locate, obtain, and document DHS microdata and codebooks.
• Build an empirical strategy with appropriate use of sampling weights and survey design.
• Implement descriptive and causal analyses suited to data limits, and state identification assumptions explicitly.
• Discuss limitations of own work.
• Produce reproducible code, tables, and figures.
• Present results clearly and respond to technical questions.

• Attend and participate in all sessions. Two absences allowed with our without justification. 

• Presence is required for presentations.

• Short lectures to introduce methods and workflows.

• Hands-on labs using DHS with instructor support.

• Proposal and results workshops with structured peer review.

• Feedback on code, design, and presentation.

• Initial presentation – 33%
  Clearly state question, motivation, strategy, sample, variables.

• Final presentation – 33%
  Show clean tables and one figure. Report design, weights, assumptions, main result, and limits. Slides required.

• Write-up – 34%
  5-10 pages text plus references and appendix with tables and figure captions. Must state data source, construction, methods, assumptions, and limitations. Reproducible repository submitted with code and README.

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.