Leaving Theory Behind: Why Hypothesis Testing Has Become Bad for IR
Theory creating and hypothesis testing are both important elements of social science. Unfortunately, in recent years the balance between theory creation/refinement and the testing of empirical hypotheses has shifted sharply toward the latter. This trend is unfortunate, because insufficient attention to theory can lead to misspecified models and overreliance on misleading measures of key concepts. In addition, the poor quality of much of the data in IR makes it less likely that these efforts will produce useful cumulative knowledge. The shift away from theory and towards hypothesis testing is due mostly to the professionalization of academia, and this trend is likely to continue unless there is a collective decision to alter prevailing academic incentives.
|Date of creation:||Jan 2013|
|Date of revision:|
|Contact details of provider:|| Postal: 79 JFK Street, Cambridge, MA 02138|
Web page: http://www.ksg.harvard.edu/research/working_papers/index.htm
More information through EDIRC
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Christopher Blattman & Edward Miguel, 2010.
Journal of Economic Literature,
American Economic Association, vol. 48(1), pages 3-57, March.
- Christopher Blattman & Edward Miguel, 2009. "Civil War," NBER Working Papers 14801, National Bureau of Economic Research, Inc.
- Blattman, Christopher & Miguel, Edward, 2009. "Civil War," Center for International and Development Economics Research, Working Paper Series qt90n356hs, Center for International and Development Economics Research, Institute for Business and Economic Research, UC Berkeley.
When requesting a correction, please mention this item's handle: RePEc:ecl:harjfk:rwp13-001. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ()
If references are entirely missing, you can add them using this form.