[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]

2023-11: Warosu is now out of extended maintenance.

/sci/ - Science & Math

File: 78 KB, 412x351, Happy-Sad-Frog-08.png [View same] [iqdb] [saucenao] [google]

7932685

Anonymous Mon Mar 14 19:08:38 2016 No.7932685 [Reply] [Original]

>tfw your p-value is 5.01

>>	Anonymous Mon Mar 14 19:13:59 2016 No.7932691 >2016 >using p-values

>>	Anonymous Mon Mar 14 19:25:29 2016 No.7932711 Like it matters. Who cares what your hypothesis is or if you accept or reject it? I don't understand why you need one in the first place. I like just exploring and playing around with shit to see what happens. The rest is formalistic autism.

>>	Anonymous Mon Mar 14 19:30:53 2016 No.7932719 Nigga I've seen Nature articles where graphs had correlation coefficients less than .8 (granted, it was biology, but still). You might not be the worst hack to make it in this world

>>	Anonymous Mon Mar 14 19:36:47 2016 No.7932728 >>7932719 you can't assess the quality of a correlation score without also assessing the noise inherent in the system for some systems, a coefficient of 0.8 is pretty nice.

>>	Anonymous Mon Mar 14 19:39:09 2016 No.7932733 Very recent and very related https://www.amstat.org/newsroom/pressreleases/P-ValueStatement.pdf Google if you want to learn more

>>	Anonymous Mon Mar 14 19:45:18 2016 No.7932741 >>7932685 That's good you mong That means you have probably found something interesting