Who killed statistical significance?

I nominate John Ioannidis, Gerg Gigerenzer, Jacob Cohen, and (now) @aubreyclayton! Somehow, I missed Aubrey Clayton’s powerful take-down of standard statistics and “statistical significance,” which was published in Issue #74 of Nautilus (August 1, 2019). Among other things, Clayton explains why probability without priors is impossible, and he presents three striking examples of bad statistical reasoning–the Sally Clark case, cancer screening, and a bullshit study that was published in the journal Science–and shows step-by-step why Bayesian reasoning outperforms so-called significance testing every time. I only wish to add that Bayesian reasoning also solves many so-called “proof paradoxes” in law, including Larry Tribe’s blue bus problem and the paradox of the gatecrasher. On the blue bus problem, check out my full-length law review article “Visualizing Probabilistic Proof,” and for the so-called paradox of the gatecrasher, check out my October 2014 blog post titled “The paradox of the gatecrasher is not a paradox.” Any questions?

There is no Theorem but Bayes' and Laplace is His Prophet | Alea deum

About F. E. Guerra-Pujol

When I’m not blogging, I am a business law professor at the University of Central Florida.
This entry was posted in Uncategorized. Bookmark the permalink.

3 Responses to Who killed statistical significance?

  1. Craig says:

    Enrique, you are a genius — your mind runs at such a higher gear, I would be intimidated to have a conversation with you. (This comment pertains less to this post than to your blog in general.)

Leave a Reply

Fill in your details below or click an icon to log in:

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 )

Connecting to %s