Helpful Articles

Adding to Bill Henderson's wonderful post, ELS on the Cheap, I thought I share some articles I have found immensely helpful in doing empirical work--pieces that describe common issues, what not to do (and what most people do anyway and what problems arise), and what to do instead.

1.  Panel Data

Beck, Nathaniel and Jonathan N. Katz. 1995. “What to Do (and Not to Do) with Time-Series Cross-Section Data.” American Political Science Review 89:634-47.

Wilson, Sven E. and Daniel M. Butler. 2004. “A Lot More to Do: The Promise and Peril of Panel Data in Political Science.” Working Paper.  (forthcoming in Political Analysis).

2.  Interaction Variables

Brambor, Thomas et al. 2006. "Understanding Interaction Models: Improving Empirical Analyses." Political Analysis 14: 63-83.

3.  Presentation of Results

King, Gary et al. 2000. "Making the Most of Statistical Analyses: Improving Interpretation and Presentation." American Journal of Political Science 44: 341-55.

There are many more.   What are some other readers' favorites?

Comments

[Michael Heise]

A recent piece by Ted Eisenberg and Marty Wells in JELS (3:1, 175-95) helpfully reminds all to, among other things, carefully follow data and check OLS regression assumptions. A useful methodological "primer."

http://www.blackwell-synergy.com/toc/jels/3/1

[Jason Czarnezki]

Steve,

This link should help for those new to ELS (it links to why most use STATA among other things).

http://www.elsblog.org/the_empirical_legal_studi/2006/05/new_empirical_l.html

[Steve Erickson]

Great post. As someone new to the ELS area, I'm wondering if there are any good books that provide an overview of the field. I'm also curious as to why ELS's prefer STATA over other applications.

[Tracy Lightcap]

My favorite (an oldie, but a goodie):

John Tukey. 1986. Data analysis and behavioral science or learning to bear the quantitative man's burden by shunning badmandments. In The Collected Works of John Tukey, Vol. 3, ed. Lyle V. Jones. New York: Chapman and Hall.

Originally published in 1961(!), this is STILL relevant. I've been trying to avoid the badmandments ever since I read this piece. Would that our colleagues who like "positive theory" had read this piece as grad students.

Another good one from the master:

Frederick Mosteller and John Tukey. 1986. Data analysis, including statistics. In The Collected Works of John Tukey, Vol. 3, ed. Lyle V. Jones. Murray Hill, NJ: Bell Labs.

Published in 1968. We still haven't caught up with this.