News for hackers. Stuff that matters.
Re:Tether price manipulation by dsr_ on Friday January 08, 2021 @07:24AM (#25683936)
While correlation is not causation, correlation is evidence for causation... and there's a lot of correlation in those graphs.
Re:Tether price manipulation by jwalton on Friday January 08, 2021 @07:48AM (#25684116)
Correlation is definitely not evidence for causation. Also, if you reverse the cause and effect, what analysis do you get? When BTC prices are in the rise, it’s because people are putting money into crypto currencies. When people are putting money into crypto, some of that money is probably going into tether, so there’s more demand for tether, so Bitfinex increases the supply. With this reasoning, we get exactly the same graph with a totally different meaning.
Re:Tether price manipulation by callamdelaney on Friday January 08, 2021 @08:01AM (#25684214)
> Correlation is definitely not evidence for causation.

Try telling this to climate change activists

Re:Tether price manipulation by tomwojcik on Friday January 08, 2021 @07:33AM (#25684000)
It literally is not.
Re:Tether price manipulation by wegs on Friday January 08, 2021 @07:41AM (#25684049)
Correction: Correlation is evidence for causation. It's weak evidence, and generally speaking, stronger correlation isn't more evidence.

There's a gradual process to go from hypothesis to theory to fact, and to get there, you need several types of independent evidence. Correlational evidence is okay as one of those.

A correct statement is that correlation is not proof of causation (no matter how strong).

Types of evidence:

* Correlation

* Theoretical basis / strong hypothesis

* Extrapolation

* Interpolation

* Small-scale well-controlled experiments (lab setting)

* Large-scale less controlled experiments (real-world setting)

* Anecdotes

* ... and so on

You want several of those before you start to believe anything, and some are stronger than others. Correlation isn't fundamentally weaker than most of those, though; all of those carry their own methodological issues. The number of times you can have a large-scale perfectly-controlled preregistered randomized control trial with no confounding effects is exceptionally rare (some medical trials, and a few other settings).

Re:Tether price manipulation by benibela on Friday January 08, 2021 @11:59AM (#25686719)
But it is

There are several algorithms that calculate the causal structure from correlations: PC, GES, FGS, FCI

They are proven to be asymptotically correct

Re:Tether price manipulation by arvindamirtaa on Friday January 08, 2021 @07:40AM (#25684044)
>"...correlation is evidence for causation"

Yeah...that's not how it works.

Re:Tether price manipulation by kilnr on Friday January 08, 2021 @08:27AM (#25684469)
I assume you've conflated evidence and proof?
Re:Tether price manipulation by arvindamirtaa on Friday January 08, 2021 @04:01PM (#25690456)
Causation may be evidence for correlation. But the reverse is simply not true.