[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y ] [Search | Home]
4Archive logo
If correlation doesn't equal causation,...
If images are not shown try to refresh the page. If you like this website, please disable any AdBlock software!

You are currently reading a thread in /his/ - History & Humanities

Thread replies: 35
Thread images: 5
File: 1439821938389.jpg (72 KB, 600x600) Image search: [iqdb] [SauceNao] [Google]
1439821938389.jpg
72 KB, 600x600
If correlation doesn't equal causation, what does? And why can't you trust it even when variables are isolated? Why statistics?
>>
>>675761
what if they are both caused by the same thing
>>
>>675761
You can't control for all variables till you know all variables. And there are unknown unknowns so this is impossible.
>>
dude i thought that was a vagina
>>
>>675761
Counterfactual dependence.
>>
File: 1452890063799.jpg (112 KB, 634x799) Image search: [iqdb] [SauceNao] [Google]
1452890063799.jpg
112 KB, 634x799
>>675814
>>
>>675830
Do most people see an ass?

That's what I see.
>>
>>675830
What is that a picture of?
>>
>>675870
little baby smooches
>>
>>675870
a hairy bald man kissing a baby
>>
>>675830
Kek..looks like a sick dude is shoving his ass to that baby face.
>>
File: impotence.png (648 KB, 500x709) Image search: [iqdb] [SauceNao] [Google]
impotence.png
648 KB, 500x709
>>675761
>what are p-values
>what are confidence intervals
>what are double blind experiments
>>
>>675884
Ways to reduce bias but everyone still says what's in OP
>>
>>675875
NOW I SEE IT!
>>
>>675892
Then they're retards. No true causation can be proved empirically but we can be arbitrarily sure of the likelihood of causation with tools of statistics and probability.
>>
>>675761
Sequential 100% correlation implies that the first in the sequence is the causation of that which always follows.
>>
>>675761
>If correlation doesn't equal causation, what does?
Causation equals causation, you fucking retard.
>>
>>675899
>arbitrarily sure of the likelihood


what a nice fantasy
>>
>>675909
Which comes from what?
>>
File: 1451217965866.jpg (36 KB, 640x427) Image search: [iqdb] [SauceNao] [Google]
1451217965866.jpg
36 KB, 640x427
>>
>>675761
>if correlation doesn't equal causation, what does?
causation

There's a correlation between women's hemline lengths and economic performance (read about hemline theory, it's actually kind of neat) but it would be foolish to say that the length of women's hemlines causes economic booms and busts (although the converse could possibly hold true).
>>
>>675761
Correlation could be the result of causation, but it doesn't prove it, you have to find the causal link.
>>
Since everyone went for the low hanging fruit, let me ask more directly.
Where do causal links come from? When does someone get to say "yep, that's it"?

You all just say causality as if every truth was always understood and we can't find more of them.

Or are you all just saying this shit because no one knows?
>>
>>677796
>Where do causal links come from?

From our own pattern seeking minds, and our limited experience
>>
>>677801
How is naive observation better than statistics?
>>
>>677796
>Where do causal links come from? When does someone get to say "yep, that's it"?
when someone says it. human perception is unreliable and so is human commentary.
>>
>>675761
Is that supposed to look like a hairy moins veneris?
>>
>>677796
you want us to explain to you what a causal link is?

https://en.wikipedia.org/wiki/Causality
>>
>>675761
>>677796
Experimental designs where independent variables are manipulated and dependent ones are observed can often times be internally valid (which allows us to infer causation), rather than correlation studies where coinciding variables are studied.

There are many degrees of experimental designs which further ensure causal relationships. The best I can think of at the top of my head are double blind drug studies. Even if we weren't sure at which step the affect is produced, you be a special kind of retarded if you claimed the results are just correlation.
>>
>>677880
/thread
I know I can't thread my own comment, and I'm by no means claiming to be definitely right (look into it on your own), but given the IQ of pretty much all the other responses I'd just hedge your bets on this one.
>>
>>677814

Neither are flawless, but through observation you usually get more nuances than you would in a normal distribution
>>
File: hairy.jpg (15 KB, 398x580) Image search: [iqdb] [SauceNao] [Google]
hairy.jpg
15 KB, 398x580
>>675761
You can reliably isolate factors with chemometrical/multivariate statistic methods.

PCA, dendrites, clusters etc. can reliably pinpoint which factors are important.
>>
>>675875
>hairy bald man
OXYMORON
>>
>>677538
There is a pussy in there.
>>
>>678253
See an eye, first time, every time.
Thread replies: 35
Thread images: 5
Thread DB ID: 517032



[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y] [Search | Home]

[Boards: 3 / a / aco / adv / an / asp / b / biz / c / cgl / ck / cm / co / d / diy / e / fa / fit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mu / n / news / o / out / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / t / tg / toy / trash / trv / tv / u / v / vg / vip /vp / vr / w / wg / wsg / wsr / x / y] [Search | Home]

All trademarks and copyrights on this page are owned by their respective parties. Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
This is a 4chan archive - all of the shown content originated from that site. This means that 4Archive shows their content, archived. If you need information for a Poster - contact them.
If a post contains personal/copyrighted/illegal content, then use the post's [Report] link! If a post is not removed within 24h contact me at [email protected] with the post's information.