Top all-time · #11518
Probable Error
Personal blog · mchankins.wordpress.comsciencemath
Probable Error is a personal blog at mchankins.wordpress.com about science and math. Since 2013, 7 different Hacker News readers have linked it 10 times, most often “Still Not Significant”. The last post was in 2018, but the archive is still widely read.
Too few sampled comments (7) to say how often HN recommends it.?
Why HN links it
HN readers link Probable Error mainly for its #stillnotsignificant posts, which criticise misuse of statistical significance and p-values in research and replication failures in published papers.
Summarised by Claude from a sample of 7 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
I don't mean to sound critical, but I am; so that's how it comes across
Most-linked posts?
- Still Not Significant3 people · 3 mentions · first linked 2013-05-14
- Still Not Significant (2013)2 people · 5 mentions · first linked 2015-11-17
What Hacker News says?
Verifiable facts and accountability are often more important than individual interpretations of a singular theory of "truth". https://en.wikisource.org/wiki/The_Blind_Men_and_the_Elephan... If one is cooking their data, it is only slightly worse than creating entire fake journals to publish self-serving content for political arguments (true story). I hold particular disdain for the chaos faction after taking 20 minu…
Comment linking /2013/04/21/still-not-significant-2/
on “What not to say to someone who has just been laid off”Submitted Still Not Significant as a story · 2 points
HN discussionWow, this is quite stunning to read. He actually baldly states that the only reason for experimenting is to confirm what you already believe, and that you should therefore just do as many experiments as it takes to 'prove' yourself correct, hide evidence of the failures and then stop - forever. This was linked from the article, BTW - and the responses they also linked to are dead on: http://mchankins.wordpress.com/2…
Comment linking /2014/07/12/do-not-replicate
on “Replication Controversy in Psychology”Submitted Still Not Significant (2013) as a story · 1 points
HN discussionFrom post down the page by tekp2 - https://news.ycombinator.com/item?id=7836326 http://phenomena.nationalgeographic.com/2014/06/02/why-have-... "But Lazo thinks that neither the archival analysis nor the psychological experiments support the team’s conclusions. For a start, they analysed hurricane data from 1950, but hurricanes all had female names at first. They only started getting male names on alternate years in…
Comment linking /2013/04/21/still-not-significant-2/
on “Feminine-named hurricanes are deadlier than masculine-named hurricanes”Submitted Still Not Significant as a story · 1 points
HN discussionWith data quality standards, research ethics, and random audits. https://mchankins.wordpress.com/2013/04/21/still-not-signifi... The primary issue is circular references in citation, and non-cascaded retractions for known errata. Typically thesis work tends to be reproducible most of the time, but around 12% to 17% of the hundreds of papers I read every month were nongeneralizable or worse outright BS. It can be rea…
Comment linking /2013/04/21/still-not-significant-2/
on “How Should We Critique Research? (2019)”Immediately reminded me of #stillnotsignificant: http://mchankins.wordpress.com/2013/04/21/still-not-signific... (see also the hashtag on Twitter)
Comment linking /2013/04/21/still-not-significant-2/
on “Science Is Broken”Sycophantic idealism mixed with political Brand analytical-blindness is incompatible with functional democratic processes. Verifiable facts are the core responsibility of the Scientific process, and a lot of people still fail that minimal standard. https://mchankins.wordpress.com/2013/04/21/still-not-signifi... Modern corruption is just unsustainable populist negligence, that coincidentally also collapsed many empir…
Comment linking /2013/04/21/still-not-significant-2/
on “The Responsibility of Intellectuals”Still not significant: https://mchankins.wordpress.com/2013/04/21/still-not-signifi... Nothing like spending 10 minutes reading a paper to see results which are likely nonsense. However, it pales in comparison to spending 3 weeks trying to replicate popular works... only to find it doesn't generalize... you know that ROC was likely from cooked data-sets confounded with systematic compression artifact errors... likel…
Comment linking /2013/04/21/still-not-significant-2/
on “P < 0.05 Considered Harmful”