When Evidence Says No, but Doctors Say Yes - The Atlantic
Wonderful to see the "A decade of reversals" paper find an audience outside of academia. Also love the term "bio-plausible" to explain how stupid procedures survive simply because it seems obvious that they should work.
health  medicine  statistics  science 
15 hours ago
People Make The World Go Round by manuel0 | Manuel Aristaran | Free Listening on SoundCloud
Just recorded this little cover of a classic tune by The Stylistics: «People Make the World Go Round"
from twitter_favs
3 days ago
Twitter
These people think they can be the master race, but they're legit scared of European suburbs
from twitter_favs
4 days ago
Twitter
Strange to see a book written by my parents still laying around on the occasional NZ bookshelf...
It was published…
from twitter_favs
4 days ago
Lie in the Sky – @DFRLab – Medium
RT : . But Russia lies an awful lot and does a bad job of it, so it's easy to catch them out
from twitter
4 days ago
Twitter
RT : This media outlet freed slaves trapped in cages.
from twitter
5 days ago
A man walks into a bank
"Banks don’t do business like the rest of us do business. Banks don’t do lunch to resolve an issue. They send a lawyer. Banks don’t care about your rights. They care about their rights. (Read your bank’s provided explanation of your banking rights, if you don’t believe me.) Banks don’t care about your bank balance. They care about their bank balance. And what banks really don’t do is take responsibility for their mistakes. They enforce penalties for ours."
economics  banking  ethics 
6 days ago
Twitter
I don't think you beat conspiracy theories by becoming a conspiracy theorist... never was there a better time for s…
from twitter_favs
7 days ago
Rolf Zwaan: The Dripping Stone Fallacy: Confirmation Bias in the Roman Empire and Beyond
"There is a black stone called the Dripping Stone, captured originally from the Etruscans and stored in a temple of Mars outside the city. We go in solemn procession and fetch it within the walls, where we pour water on it, singing incantations and sacrificing. Rain always follows--unless there has been a slight mistake in the ritual, as is frequently the case."

"And of course nobody bothers to look for small errors in the ritual when it is raining cats and dogs, or for hidden moderators when p<.05"
science  statistics 
8 days ago
BayesFactor: Software for Bayesian inference: How to train undergraduate psychologists to be post hoc BS generators
"The assignment: Students are assigned an article from a peer-reviewed psychological journal and asked to critique it. [...] The basic problem with this assignment is that students are not particularly well-versed in any particular psychological topic, nor in psychological research methods. On the other hand peer-reviewed articles have been reviewed by people who are, which means that whatever problems remain with the research have evaded skilled reviewers. [...] Upon reading such an article and having difficulty find a critique, a student is in an awkward position: they must write an essay. So what do they do? They come up with whatever critiques come to mind, which are likely to be low-quality critiques. I suspect readers of this blog have experienced these sorts of critiques in student assignments: maybe there are cultural differences? The sample seems small. Are these really the best stimuli to use? They must choose a number of these arguments, and argue for them, in spite of the fact that they don't have sufficient knowledge on which to base such a critique. We're training them in the fine art of bullshit."
psychology  science  education  teaching 
8 days ago
Nobody Knows What They're Doing
"This is the most pervasive of of all Washington legends: that politicians in Washington are ceaselessly, ruthlessly, effectively scheming. That everything that happens fits into somebody's plan. It doesn't. Maybe it started out with a scheme, but soon enough everyone is, at best, reacting, and at worst, failing to react, and always, always they're doing it with less information than they need."
politics 
8 days ago
Twitter
Wow—this is quite the letter to the editor.
from twitter_favs
8 days ago
4 redenen waarom onderzoeksjournalistiek noodzakelijk is - Luc Pauwels
Over journalistiek in post-truth tijden. Effe in eigen boezem kijken, toch.
from twitter_favs
10 days ago
Untitled (https://osf.io/preprints/psyarxiv/q46q3)
Check out our new preprint, Introduction to Bayesian Inference for Psychology:
Some magical examples in there. ;-)
from twitter_favs
11 days ago
Getting critical with data literacy - zararah.net Zara Rahman
I wrote a quick post about critical data literacy, with a big shout out to :
from twitter_favs
11 days ago
Twitter
ICYMI, we just finished our first week of a few lil' changes at Vox Media.
from twitter_favs
13 days ago
How Can Medical Professionals Avoid Making Assumptions That Lead to Mistakes?
Most doctors, like everyone, are bad at understanding probability. This is a problem. Excellent piece.
from twitter_favs
14 days ago
OpenNews Ascent Stage Initiated | OpenNews
And I will be taking on a new role with : Deputy Director. Woohoo.
from twitter_favs
15 days ago
Science: Hans Rosling – data rock star
RT : Here's 's 2014 profile of Hans Rosling. He was an inspiration to all who tell stories with data:
from twitter
16 days ago
Expressing value statements with measures | niksilver.com
Expressing value statements with measures - New on the blog...
from twitter_favs
16 days ago
Twitter
New script for automatically transforming boundaries into rectangles. Check out the repo:…
from twitter_favs
16 days ago
Twitter
This story about George Formby and his wife Beryl's trip to South Africa always cheers me up.
from twitter_favs
22 days ago
Unlearning descriptive statistics
Unlearning descriptive statistics (and learning better ones) – new post!
from twitter
22 days ago
Untitled (https://motherboard.vice.com/en_us/article/big-data-cambridge-analytica-brexit-trump)
Arrêtez tout et lisez cette enquête incroyable sur le rôle joué par des experts big data dans la victoire de Trump
from twitter_favs
24 days ago
Twitter
A new header for a new chapter in my life.
from twitter_favs
27 days ago
Twitter
This opening paragraph sounds like an acid trip. Actually, the whole article.
from twitter_favs
29 days ago
[Weekly Review] | January 25, 2017, by Joe Kloc | Harper's Magazine
This opening paragraph sounds like an acid trip. Actually, the whole article.
from twitter_favs
29 days ago
Calling Yourself ‘Humbled’ Doesn’t Sound as Humble as It Used To - The New York Times
"We bow our heads in recognition of this thing that’s bigger than us, than our massive egos, and we’re humbled by its immensity. And why not? It’s got to be huge to eclipse us."
culture  society  language 
29 days ago
Twitter
I've solved climate change. Guardian needs to remove this dangerous button NOW. Irresponsible!
from twitter_favs
5 weeks ago
Twitter
Shaved and feeling pretty.
from twitter_favs
5 weeks ago
Why newsrooms need storytelling tools and what we’ve learned building them
Since many have asked: Yes, we plan to open-source (at least parts of) our toolbox sometime soon.
from twitter_favs
5 weeks ago
How statistics lost their power – and why we should fear what comes next | William Davies | Politics | The Guardian
"When macroeconomics is used to make a political argument, this implies that the losses in one part of the country are offset by gains somewhere else. Headline-grabbing national indicators, such as GDP and inflation, conceal all sorts of localised gains and losses that are less commonly discussed by national politicians. [...] So when politicians use national indicators to make their case, they implicitly assume some spirit of patriotic mutual sacrifice on the part of voters: you might be the loser on this occasion, but next time you might be the beneficiary. But what if the tables are never turned?"

Interestingly the solution might be more statistics, not less: we might for example demand of politicians not just increased employment or health, but also (or even exclusively) the reduction of disparities. And disparities are easily quantified as statistical deviations (SD, MAD).
statistics  history  society  politics 
5 weeks ago
Twitter
Woke Empire update: MLK edition
from twitter_favs
5 weeks ago
Who killed the curry house? | Bee Wilson | Life and style | The Guardian
Interesting snippet from a great read on the decline of the British curry house.
from twitter_favs
6 weeks ago
Twitter
Interesting snippet from a great read on the decline of the British curry house.
from twitter_favs
6 weeks ago
Susan Gelman's Response to "Lure of Luxury" | Boston Review
"The psychologist Paul Rozin notes that people seem to operate according to a principle of “magical contagion,” where one can be harmed by contact with an object involved with evil or death, leading people to reject wearing Hitler’s sweater, a suit that someone died in, or a house in which a murder was committed."
psychology  cognition  morality 
6 weeks ago
Istanbul: A Magical Place Before The Violence Began - Vogue
«I learned that the future will never be predictable. Mutual dependence in daily life is the truest form of safety.»
from twitter_favs
7 weeks ago
C3TV - SpiegelMining – Reverse Engineering von Spiegel-Online
Fascinating talk (in German) on how to discern a news org's Internal structure by scraping & analysing its output:
from twitter_favs
7 weeks ago
Twitter
The Dress, but for data journalists.
from twitter_favs
7 weeks ago
Headlines matter » Nieman Journalism Lab
"In 2017, it will be clearly inadequate to excuse a bad headline on the grounds that anybody who hasn’t read the full 4,500-word story is unqualified to pass judgment."

"In practice, this is going to mean that the purview of headlines needs to be wrested back from social-optimization teams. Instead, the people who know the story best — including the people who actually wrote the thing — have to be empowered to veto all headlines which are in any way misleading."
ethics  journalism  analytics 
8 weeks ago
News after advertising may look like news before advertising » Nieman Journalism Lab
"To understand what this means for journalism, what news might look like after advertising, it is worth considering what news looked like before advertising, before the rise of the penny press."

"Some pre-advertising news media worked for business interests / Other pre-advertising news media worked for governments and political parties / Finally, some pre-advertising news media were parts of social movements"
journalism  media  business  advertising  future 
8 weeks ago
Twitter
Finally cleaned my desk and found three practically new phones with unsupported operating systems.
from twitter_favs
8 weeks ago
Twitter
A preprint of our Guide to Teaching is now up! With
from twitter_favs
9 weeks ago
FTAV Person of Interest 2016: the longlist | FT Alphaville
Petition to only refer to this site as the "banefully ephemeral squawk mortar"
from twitter_favs
9 weeks ago
Twitter
Petition to only refer to this site as the "banefully ephemeral squawk mortar"
from twitter_favs
9 weeks ago
Twitter
Remember that article? That was a good article.
from twitter_favs
10 weeks ago
Twitter
But: what if all of this is hot air and the web will continue to evolve incrementally? Have a strategy for that?
from twitter_favs
10 weeks ago
Twitter
.’s Client Email Helper is a little freelancing master class right there thx…
from twitter_favs
10 weeks ago
Jessica Hische - Client Emails Are Hard.
.’s Client Email Helper is a little freelancing master class right there thx…
from twitter_favs
10 weeks ago
As Trumplethinskin lets down his hair for tech, shame on Silicon Valley for climbing the Tower in silence - Recode
Here's my 1st weekly column, where I go all tsk-tsk on tech for allowing itself to be disrupted by Trump so easily:
from twitter_favs
10 weeks ago
5 unexpected sources of bias in artificial intelligence | TechCrunch
5 unexpected sources of bias in artificial intelligence (In the end, machines are only human.) via
from twitter_favs
10 weeks ago
Twitter
I keep coming back to this passage about hegemonic "resilience" from and I'm haunted by how our manifold fa…
from twitter_favs
10 weeks ago
An ode to the bar chart
If you can't say it with a bar chart, try again. New post!
from twitter
10 weeks ago
« earlier      
academia academic advertising advice aggregation agile ai algorithm analysis analytics api apple apps architecture arduino art audio authentication bayesian bbc bestpractices bias biology blogging blogs books branding business caching career casestudies cities cli clothing cloud cms coding cognition collaboration college comments communication community comparison conference content-strategy context cooking copyright creativity critique crowdsourcing css culture curation data database databases datamining datascience democracy deployment design development devops disruption diy django drawing drupal dtp economics education electronics email entrepreneurship ethics europe extendscript facebook factchecking failure fashion filetype:pdf food frameworks freelancing french functional future gaming gent geo gis google gov2.0 government graphics guardian hardware haskell health hiring history html5 humor hyperlocal ia icons impact informatica information information-architecture innovation inspiration internet interview ip javascript journalism jquery language law layout learning library life lifehacks linked-data linux literature local london longform machinelearning management mapping marketing mashups math mathematics media media:document medicine metadata methodology metrics mistakes ml mobile motivation music news newspapers newsrooms nhst niche nlp nonprofits nosql nytimes office online opendata opengov opensource payment paywall paywalls performance philosophy photography politics postdigital pr pricing probability process productivity programming projectmanagement psychology publishing python qa r rationality rdf reading reasoning reference replication reporting reproducible research resources rest robotics saas scalability science scraping search security semanticweb showcases social socialmedia society sociology software spanish ssk startup startups statistics storytelling strategy study style subsidies sysadmin tagging taxonomy teaching team technology testing timelines to-evaluate to-read to:tumblr tools transparency travel trends truth tutorial tutorials twitter typography ui usa usability ux video videojournalism visualization volunteering web webdesign webdev webservices wiki wikipedia women work workflow writing yahoo youtube

Copy this bookmark:



description:


tags: