Thomas J. Leeper > Teaching > Experiments Course > Home

Experimental Methods Seminar

This course addresses experimentation as a research method in political science. It is being taught as a master seminar at Aarhus University during Spring term 2014. The Spring 2014 version of the class focuses on experimental design.

Syllabus

You can find an outline of the course objectives, schedule for the course, exam structure, and assigned readings in the Syllabus.

Readings

In addition to journal articles on the syllabus, the course will use the following textbook:

William R. Shadish, Thomas D. Cook, and Donald T. Campbell. Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Houghton-Mifflin, Boston, MA, 2001.

Though not required, the following is also highly recommended for those interested in issues of experimental analysis:

Alan S. Gerber and Donald P. Green. Field Experiments: Design, Analysis, and Interpretation. W.W. Norton, 2012.

Shadish et al. provide a useful conceptual background for the practice of causally oriented social research. Gerber and Green supplement this text with an explicit focus on experimental design and analysis in the modern language of the Neyman-Rubin potential outcomes framework.

Slides

Course slides are available in the /Slides directory.

Assignments and Exam

Weekly Assignments

In preparation for the exam, students will prepare and present short (less than one page), bullet-point summaries of example experiments reported in published articles. These short assignments will help students to interpret experimental work and practice the structure of the final assignment. The basic topics that should be included in these summaries are:

  1. Research question(s)
  2. Hypotheses
  3. Experimental design and conditions
  4. Measurement of outcomes and key covariates
  5. Sampling and random assignment procedures
  6. Problems with implementation and their remedies
  7. Analysis
  8. Findings

A worksheet is available that can be used to guide the completion of these assignments.

Exam, synopsis presentations, and one-on-one meetings

The exam for the course involves a home assignment (total 8000 words) laying out the design and analysis of a proposed experiment. The syllabus describes the requirements for this assignment in detail.

Students will present a synopsis of their experimental design during on April 8th in order to receive peer feedback.

Student can then, optionally, meet individually with the instructor before the exam is due to receive additional feedback.

Why GitHub?

Read more about why this course is on GitHub here.