(Irrelevant?) Correlations...

How does science work? And what's all this about quantum mechanics?

Moderators: AMod, iMod

Post Reply
User avatar
skakos
Posts: 287
Joined: Mon Mar 25, 2013 7:22 pm
Location: Athens, Greece
Contact:

(Irrelevant?) Correlations...

Post by skakos »

Software discovers correlations between unrelated events. [http://www.popsci.com/article/science/a ... -accidents, http://www.tylervigen.com/]


Example: Number of people dying from being tangled int their bedsheets - Ski facilities revenues

Image
Correlation: 0.969724


But if there is a correlation why are they... unrelated?

Even after all these years of "progress", the best way to "see" something is still just to... choose to see it.
Without any reason. Or maybe there is a reason? Let me check the imports of Norwegian oil...

What really makes us see correlations somewhere and not somewhere else, EVEN THOUGH the data say so?

Our beliefs seem to drive our knowledge...
jackles
Posts: 1553
Joined: Sat Aug 17, 2013 10:40 pm

Re: (Irrelevant?) Correlations...

Post by jackles »

yeah have noticed these unbelievably complex patterns in the event.could it be that as an individual becomes more enlighten in consciousness he takes up the position more and more of a singlarity to these event patterns.they become as it where entangled with his journey to enlightenment.
User avatar
WanderingLands
Posts: 819
Joined: Wed Jan 08, 2014 3:39 am
Contact:

Re: (Irrelevant?) Correlations...

Post by WanderingLands »

I think that the explanation would be Synchronicity, which was an idea made by psychologist Carl Jung. It's the idea of two or more events occurring in an orderly fashion instead of merely being coincidental.
mickthinks
Posts: 1816
Joined: Thu Oct 18, 2007 1:10 am
Location: Augsburg

Re: (Irrelevant?) Correlations...

Post by mickthinks »

Software discovers correlations between unrelated events. [...] Example: Number of people dying from being tangled int their bedsheets - Ski facilities revenues

But given that both are closely related to the population figures, I would expect them to be correlated.
User avatar
SpheresOfBalance
Posts: 5725
Joined: Sat Sep 10, 2011 4:27 pm
Location: On a Star Dust Metamorphosis

Re: (Irrelevant?) Correlations...

Post by SpheresOfBalance »

skakos wrote:Software discovers correlations between unrelated events. [http://www.popsci.com/article/science/a ... -accidents, http://www.tylervigen.com/]


Example: Number of people dying from being tangled int their bedsheets - Ski facilities revenues

Image
Correlation: 0.969724


But if there is a correlation why are they... unrelated?

Even after all these years of "progress", the best way to "see" something is still just to... choose to see it.
Without any reason. Or maybe there is a reason? Let me check the imports of Norwegian oil...

What really makes us see correlations somewhere and not somewhere else, EVEN THOUGH the data say so?

Our beliefs seem to drive our knowledge...
Come on, do you actually take that algorithm seriously, or rather the way one overlays what it is that it means. There is actually much coincidence in the world, when considering billions of things to compare. Sometimes a cigar is just a cigar!
User avatar
skakos
Posts: 287
Joined: Mon Mar 25, 2013 7:22 pm
Location: Athens, Greece
Contact:

Re: (Irrelevant?) Correlations...

Post by skakos »

WanderingLands wrote:I think that the explanation would be Synchronicity, which was an idea made by psychologist Carl Jung. It's the idea of two or more events occurring in an orderly fashion instead of merely being coincidental.
Could be. Such cases really test our belief in data and the way we formulate theories to interpret them...
User avatar
NielsBohr
Posts: 219
Joined: Sat Aug 02, 2014 6:04 pm
Location: Switzerland
Contact:

Re: (Irrelevant?) Correlations...

Post by NielsBohr »

skakos wrote: But if there is a correlation why are they... unrelated?

Even after all these years of "progress", the best way to "see" something is still just to... choose to see it.
Without any reason. Or maybe there is a reason? Let me check the imports of Norwegian oil...

What really makes us see correlations somewhere and not somewhere else, EVEN THOUGH the data say so?

Our beliefs seem to drive our knowledge...
Skakos,

First, you have to understand that there is a deep difference between simple data, and information.

Next, correlation is nearer to the coincidence than to the relation.


The term relation is in priority something defined in relational algebra. By example, if a library want to loan books to people, they must know that the relation tells that there is potentially several books for a person, but also several people for a book, and in this case, there is a priori no possible correspondance, as we have "several for several". We have to insert a new entity, simply called "Loans", what will solve the problem when well filled with right attributes...

This illustrate the fact that relation are in priority of an understandability of (a logic of) first degree (I don't tell about second order predicates about which I don't know a lot); so relations are about to speak directly to the humain, and this is the interest.

There could be some hidden dimensions... but to see only correlation on arbitrary long period of time, is not sufficient to establish a law...

I said one time to a women moderator, somewhere else, that for a believer, the belief on one side, and God on the other, did not mean at all the the believer was faithful in God (I invoked Karl Barth and the alterity of God to help me)... at this title, some religions have not the same concept of the Soul Salvation as christians...

This is the illustration that the simultaneity is not enough to make relations.
User avatar
skakos
Posts: 287
Joined: Mon Mar 25, 2013 7:22 pm
Location: Athens, Greece
Contact:

Re: (Irrelevant?) Correlations...

Post by skakos »

I understand what you say.
But have I not put labels in the axis of the diagrams above, you would interpret them as two things which are closely related.
Indeed information is something we "see" in data.
But this is exactly the problem.
Don't you get it?
User avatar
NielsBohr
Posts: 219
Joined: Sat Aug 02, 2014 6:04 pm
Location: Switzerland
Contact:

Re: (Irrelevant?) Correlations...

Post by NielsBohr »

No, there are labels;

number of deaths on Y,
and years on X.

What don't tell that it is true for so.

Keep attention against paranoïd hypothesis, it is mentioned as prohibited in the inscription charter.

The only who can distill information from chaos is God. If no, the humain could be able to decrease entropy - and I am not sure of this.
Post Reply