If At First You Don’t Succeed, Change Alpha

In a recent working paper, posted on PsyArXiv Preprints, Daniel Benjamin, James Berger, Magnus Johanneson, Brian Nosek, Eric-Jan Wagenmakers, and 67 other authors(!) argue for a stricter standard of statistical significance for studies claiming new discoveries.  In their words:
“…we believe that a leading cause of non-reproducibility has not yet been adequately addressed: Statistical standards of evidence for claiming new discoveries in many fields of science are simply too low. Associating “statistically significant” findings with P < 0.05 results in a high rate of false positives even in the absence of other experimental, procedural and reporting problems. For fields where the threshold for defining statistical significance for new discoveries is 𝑃 < 0.05, we propose a change to 𝑃 < 0.005. This simple step would immediately improve the reproducibility of scientific research in many fields. Results that would currently be called “significant” but do not meet the new threshold should instead be called ‘suggestive.’”
To read more, 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: