William Easterly on data mining

Title says it all.  A good reminder for those of us doing quantitative research.

Advertisements

About Jake Wobig

I teach international relations and comparative politics at Wingate University in Wingate, North Carolina
This entry was posted in Miscellaneous. Bookmark the permalink.

2 Responses to William Easterly on data mining

  1. Seems a bit simplistic of an analysis for such a large accusation. Sure, this happens, but the author seems to downplay the fact that we have safeguards in the form of the accumulation of other research based around similar topics, the need to conduct valid research to both get a job/get tenure, and theory. There doesn’t seem to be much in the way of these considerations in his discussion.

    And I’m no IR/comparative scholar, but the “probability of two people belonging to ethnic groups X political assassinations” seems like a perfectly reasonable consideration; taken together with other cleavages besides ethnicity would seem to make it more likely for political conflict to occur than in more homogeneous countries. Am I wrong on that? I may very well be.

  2. Tina Mueller Zappile says:

    He is writing from the context of the economic growth literature- there are TONS of kitchen sink models for economic growth models, many including theoretically questionable control variables and many of them providing a “foundation” for some new aid program.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s