Since Nov 19th, my P value paper has been downloaded more times that total sales of my 1971 textbook! http://t.co/lFsDIx7TqI
.@hgersh2000 @signmagazine @stephensenn I fear that the case is very far from closed http://t.co/X1NEc1p2Lj
An investigation of the false discovery rate and the misinterpretation of p-values. http://t.co/MjjXw3mi09 http://t.co/aKOIv498XU
David Colquhoun on p-value Interesting, not completely convincing #repligate #pvalue #statistics http://t.co/oOMGh1m1ov
Many thanks to @stephensenn for time he spends to tell me why he doesn't agree with my take on false discovery rate http://t.co/X1NEc1p2Lj
Many thanks to @stephensenn for time he spends to tell me why he doesn't agree with my take on false discovery rate http://t.co/X1NEc1p2Lj
Many thanks to @stephensenn for time he spends to tell me why he doesn't agree with my take on false discovery rate http://t.co/X1NEc1p2Lj
Many thanks to @stephensenn for time he spends to tell me why he doesn't agree with my take on false discovery rate http://t.co/X1NEc1p2Lj
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
"An investigation of the false discovery rate and the misinterpretation of p-values": http://t.co/cRpIz3xxWY TL;DR: insist on p<0.001
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
An investigation of the false discovery rate and the misinterpretation of p-values http://t.co/FvS3vRGx9d Great Article!
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
why is p=0.05 the default & often only option considered? min false discovery rate using p values ~30%. http://t.co/A7rI1Ntfgv
@mdcearns @ConversationUK it's at http://t.co/X1NEc1p2Lj or simpler version at http://t.co/jbEqYe5N1q
.@sparrowbarley @ConversationUK @RadicalStats but that piece doesn't mention wht we DO need, the false discovery rate http://t.co/X1NEc1p2Lj
.@sparrowbarley @ConversationUK @RadicalStats but that piece doesn't mention wht we DO need, the false discovery rate http://t.co/X1NEc1p2Lj
.@sparrowbarley @ConversationUK @RadicalStats but that piece doesn't mention wht we DO need, the false discovery rate http://t.co/X1NEc1p2Lj
.@fraser_lab The promise and perils of P-values? http://t.co/O1s6S5FzrX #fljcnlt
.@fraser_lab The promise and perils of P-values? http://t.co/O1s6S5FzrX #fljcnlt
@martinnewby_1 P=0.05 vs P<0.05 refers to section 9 & 10 in http://t.co/X1NEc1p2Lj @hildabast
.@learnfromerror @hildabast I don't think so. eg no dichotomy in simulated t tests in http://t.co/X1NEc1p2Lj
.@hildabast I'd like your opinion on P < 0.05 vs P = 0.05, secs 9 and 10 in http://t.co/X1NEc1p2Lj There is no unanimity amng statisticians
.@hildabast I'd like your opinion on P < 0.05 vs P = 0.05, secs 9 and 10 in http://t.co/X1NEc1p2Lj There is no unanimity amng statisticians
@hildabast I'd be interested in your view of comment at http://t.co/Hb7so5LL6d
@hildabast link to http://t.co/X1NEc1p2Lj ? Where?
@Cleverestcookie it's because maths talent is do rare that I used simulations in http://t.co/X1NEc1p2Lj @elinlowri @mellojonny
What should be done about P values? Just change the wording? http://t.co/Hb7so5LL6d Link now works (slow moderation),
What should be done about P values? Just change the wording? http://t.co/Hb7so5LL6d Link now works (slow moderation),
"application of significance tests to observ. data, e.g. epidemiological surveys of diet and health, is not valid". http://t.co/wcC8BOkweb
You make a fool of yourself if you declare that you have discovered smth when all you are observing is random chance http://t.co/f62sM3Jnsa
An investigation of the false discovery rate and the misinterpretation of p-values by @david_colquhoun http://t.co/rojkxVwWan
Any comments welcome at http://t.co/Hb7so5LL6d on my suggestions for how P values shjould be described in papers (NOT as "significant")
Any comments welcome at http://t.co/Hb7so5LL6d on my suggestions for how P values shjould be described in papers (NOT as "significant")
Any comments welcome at http://t.co/Hb7so5LL6d on my suggestions for how P values shjould be described in papers (NOT as "significant")
What should be done about P values? Just change the wording? http://t.co/Hb7so5LL6d Link now works (slow moderation),
What should be done about P values? Just change the wording? http://t.co/Hb7so5LL6d Link now works (slow moderation),
What should be done about P values? Just change the wording? http://t.co/Hb7so5LL6d Link now works (slow moderation),
False Discovery and p values. Excellent read http://t.co/iEQO7aiM2Q via @DrDianneCrisp
An investigation of the false discovery rate and the misinterpretation of p-values by @david_colquhoun http://t.co/rojkxVwWan
An investigation of the false discovery rate and the misinterpretation of p-values by @david_colquhoun http://t.co/rojkxVwWan
The curse of p values http://t.co/gqjyMnrh2F
The curse of p values http://t.co/gqjyMnrh2F
An investigation of the false discovery rate and the misinterpretation of p-values by @david_colquhoun http://t.co/rojkxVwWan
An investigation of the false discovery rate and the misinterpretation of p-values by @david_colquhoun http://t.co/rojkxVwWan
What to do about P values? I made a siggestion at http://t.co/o8rG68pvWA Opinions very welcome
.@royalsociety arriving soon to film interview about P values and false discovery rate, so of twitter for a while http://t.co/X1NEc1p2Lj
@Sports_Pod: "If you use p=0.05 to suggest you have made a discovery then you'll be wrong at least 30% of the time" http://t.co/8uajCnhtPK
An investigation of the false discovery rate and the misinterpretation of p-values http://t.co/4iGOAsHtQq
.@royalsociety arriving soon to film interview about P values and false discovery rate, so of twitter for a while http://t.co/X1NEc1p2Lj
More on Misinterpretation of P values: http://t.co/FEi1o813LB
.@royalsociety arriving soon to film interview about P values and false discovery rate, so of twitter for a while http://t.co/X1NEc1p2Lj
An investigation of the false discovery rate and the misinterpretation of p-values: http://t.co/13DYiDl5xM
.@royalsociety arriving soon to film interview about P values and false discovery rate, so of twitter for a while http://t.co/X1NEc1p2Lj
.@GenomicsIo @raphaels7 the best link is http://t.co/X1NEc1GDCR
@GenomicsIo http://t.co/kXuniK8gmy excellent analysis of how to use (& not to use) p-values in scientific studies
An investigation of the false discovery rate and the misinterpretation of p-values | Open Science http://t.co/NQale2S5jR
An investigation of the false discovery rate and the misinterpretation of p-values | Open Science http://t.co/CbmTHREvMb #statistics
A really nice article discussing the flaws in current research #statistics http://t.co/7pwpgyoMJL @RSocPublishing
An investigation of the false discovery rate and the misinterpretation of p-values http://t.co/0S5ghqOl49
@_TheGeoff Example in Fig 1 at http://t.co/X1NEc1p2Lj gives numbers.
"If you use p=0.05 to suggest that you have made a discovery, you will be wrong at least 30% of the time" http://t.co/aTsL8tqRK1
How to avoid making a fool of yourself, from @david_colquhoun http://t.co/FckKR1BLNp
How to avoid making a fool of yourself, from @david_colquhoun http://t.co/FckKR1BLNp
.@bengoldacre said, people dislike RCTs because most bright ideas are wrong -and that means high false dicovery rate http://t.co/X1NEc1p2Lj
.@bengoldacre said, people dislike RCTs because most bright ideas are wrong -and that means high false dicovery rate http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
How to avoid making a fool of yourself, from @david_colquhoun http://t.co/FckKR1BLNp
.@bengoldacre said, people dislike RCTs because most bright ideas are wrong -and that means high false dicovery rate http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
It should be more widely understood that if you test unlikely hypotheses you are going to get many false postives http://t.co/X1NEc1p2Lj
.@bengoldacre said, people dislike RCTs because most bright ideas are wrong -and that means high false dicovery rate http://t.co/X1NEc1p2Lj
@BrownBagPantry @UrslanH if you want to understand evidence, you could start here http://t.co/X1NEc1p2Lj
Why a p-value of 0.05 might mean a 30% chance that you're wrong: http://t.co/hb6euaodkH by @david_colquhoun #phdchat
"... False discovery rate and misinterpretation of P values" by @david_colquhoun #wntrane15 http://t.co/kpMTWLML8a
How (not) to abuse p-values http://t.co/YtWAByqrsl
http://t.co/mJvYlsBXPH 生物学の論文の多くは再現性がないと問題になっているがそれもそのはずで、一般的な方法で統計処理をおこなって有意な結果を報告しようとすると、統計的必然性として再現不能な結果が量産されてしまう、というお話。
"... False discovery rate and misinterpretation of P values" by @david_colquhoun #wntrane15 http://t.co/kpMTWLML8a
False discovery rates and misinterpretation of p-values http://t.co/R0jmytbByv
A paper that links to #xkcd!? I didn't know we were allowed to do that.. http://t.co/15I9lMJ53d oh it also makes a good point about p-values
.@LouWoodley @Impactstory The fact that my paper http://t.co/ytbygLI5dv has an altmetric score of 578 shows how useless #altmetrics are
.@LouWoodley @Impactstory The fact that my paper http://t.co/ytbygLI5dv has an altmetric score of 578 shows how useless #altmetrics are