2025 RationalWiki 'Oregon Plan' Fundraiser

There is no RationalWiki without you. We are a small non-profit with no staff—we are hundreds of volunteers who document pseudoscience and crankery around the world every day. We will never allow ads because we must remain independent. We cannot rely on big donors with corresponding big agendas. We are not the largest website around, but we believe we play an important role in defending truth and objectivity.

Fighting pseudoscience isn't free.
We are 100% user-supported! Help and donate $5, $10, $20 or whatever you can today with PayPal Logo.png!
Donations so far: $10064.65Goal: $10000

File:Bayesian Beta conjugate priors vs. frequentist p-values, Ex2 from Bem (2011).svg

From RationalWiki
Jump to navigation Jump to search

Original file(SVG file, nominally 1,080 × 360 pixels, file size: 97 KB)

Experiment 2 from Bem (2011) has a binomial likelihood with k = 2,790 and n = 5,400. We can use that to evaluate two hypotheses: the outcome is compatible with chance (p=1/2) or the outcome is biased with p=55.73%. Both charts show what happens to both hypotheses plus a third (p = 2,790/5,400) as we uniformly scale both k and n, simulating the accumulation of evidence. The left-hand side uses Bayesian statistics via Beta conjugate priors, while the right-hand side uses frequentism via two-sided p-values.

File history

Click on a date/time to view the file as it appeared at that time.

Date/TimeThumbnailDimensionsUserComment
current04:48, 27 February 2025Thumbnail for version as of 04:48, 27 February 20251,080 × 360 (97 KB)Hjhornbeck (talk | contribs)

The following page uses this file:

Metadata