2 Humps = P-Hacking + Publication Bias?

In a recent blogpost at Simply Statistics, Jeff Leek announced a new R package called tidypvals: “The tidypvals package is an effort to find previous collections of published p-values, synthesize them, and tidy them into one analyzable data set.”
In a preview of coming attractions, Leek posts the following graphic, representing more than 2.5 million p-values across 25 disciplines, and asks, “Notice anything funny?”.

2Humps

Maybe it’s just that some papers report stars (*=0.10, **=0.05, ***=0.01), and don’t report p-values when estimates are insignificant.  Or maybe …
To read more, including how to download and install the tidypals package, click here.

Leave a Reply

Please log in using one of these methods to post your comment:

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

%d bloggers like this: