"The correlations were much lower between Mendeley readers and citation counts for conference papers than for journal articles in Building & Construction Engineering and Industrial and Manufacturing Engineering. Hence, there seem to be disciplinary differences in the usefulness of Mendeley readership counts as impact indicators for conference papers, even between fields for which conferences are important."
"Project Bamboo is currently piloting a directory of tools, services, and collections that can facilitate digital research. This evolution of Lisa Spiro's DiRT wiki includes new ways of browsing and commenting on the entries. Please send us feedback on how to improve the site!"
An example of R code that tests for a mediation relationship.
Resources on statistical mediation curated by David MacKinnon. Very thorough.
David Kenny's homepage. Especially useful for resources related to mediation and moderation, but also full of stuff on other sorts of statistical modelling techniques
It turns out, Google has data on enough search terms that something is always quite highly correlated with your curve! This is a crackpot conspiracy theorists dream!
I can't take this job at the moment, but maybe you can. It looks like fun!
Good story about an awesome poster about the dangers of multiple comparisons in statistics in general and in MRI work in particular.
Andrew Gelman likes this article more than the Wikipedia article on the subject.
Awesome review of cycling safety data.
This is nuts. The studies these inferences are based on have known errors and statistically insignificant results. See, for example, this: http://www.stat.columbia.edu/~cook/movabletype/archives/2009/06/of_beauty_sex_a.html How do people keep publishing this crap?
