When a study fails to replicate in political science, retractions are not very common. Often, the re-analysis that questions the original findings is published in the same or another journal; and then the original author sometimes writes a third article defending his/her findings (see here). Recently, a failed replication made it into the news, and suddenly there’s a ‘scandal.’ Here are the most important pieces you should read if you want to know the details.
Science has recently retracted a study on gay marriage, asking the research question: “Can a single conversation change minds on divisive social issues, such as same-sex marriage?”.
The retracted article failed to replicate, as political scientists David Broockman, Joshua Kalla and Peter Aronow reported in their critique of the article.
Thomas Leeper blogs about how in-house replication before journal submission can solve such issues.
Any other blogs I’ve missed? Please comment below!
Finally, I’d like to point out that I would like to see the discussion moving on towards providing tools and guidelines in the field of political science to ensure research transparency. We have our scandal, just like Psychology, Economics and Cancer Research had theirs. Now let’s start changing the field.