Randomized experiments are sometimes referred to as the “gold standard” for research studies designed to determine the causal relationship between two variables. In random control studies, individuals are randomly assigned to an intervention group or a control group in order to measure the effects of the intervention.
Topic Learning Outcome: Students will understand the characteristics of a valid randomized trial experiment and will be able to explain the value of such experiments for understanding the causal relationships between variables.
Core Concepts associated with this Topic: Random Control Trials (RCTs)
University of Toronto: PPG-1004
Stock, James H. and Mark W. Watson. 2011. Introduction to Econometrics, 3rd ed. Pearson/Addison-Wesley. Chapter 13 (p. 469-506).
George Washington: PPPA-6002
De Veaux, Richard D., Paul F. Velleman, and David E. Bock. Stats: Data and Models. Boston: Pearson/Addison Wesley, 2005. Chapter 10 (sections 10.3 – 10.5, 10.7) and Chapter 15 (sections 15.1, 15.2, 15.4).
Healey, J.H. (2011) Statistics: A Tool for Social Research. 9th Edition. Cengage Learning. Chapters 5 and 6.
Wooldridge, Jeffrey (2012). Introductory Econometrics: A Modern Approach. 4th Edition. Cengage Learning, 2012. Chapter 17.
Rutgers: Analytical Methods II
Healey (2011). Statistics: A Tool for Social Research, 9th Edition. Cengage Learning. Chapters 6 and 7.
Schroeder, Larry D., Sjoquist, David L., & Stephan, Paula E. (1986). “Understanding Regression Analysis: An Introductory Guide”. Quantitative Applications in the Social Sciences 57. Newbury Park: Sage Publications.
Possible Assessment Questions:
Page Created By: Ben Eisen and Joshua Tan, last edited 4 November, 2014.
1.) What are the advantages of randomized trials as opposed to other research designs in studying the causal relationship between two variables?
2.) Provide an example of a policy-relevant social science question for which it may be difficult to design a randomized trial (either for practical or ethical reasons). What would the challenges be?
3.) What is the difference between a random control experiment and a quasi-experimental design?
4.) What is a “natural experiment?”