There are generic terms for this sort of thing!
[A] Google for "spurious correlation" -- but note that it also has
a specific definition due to Karl Pearson, whereby two variables
not correlated between themselves give rise to two correlated
variables when each is divided by the same third variable which
is not causally related to either. Google will give you many hit
on examples which you may find useful.
[B] Have a look at the Wikipedial article:
https://en.wikipedia.org/wiki/Correlation_does_not_imply_causation
Sorry not to have time just now for a more detailed reply -- this
issue brims over with delightful examples!
Best wishes,
Ted.
On 15-Jul-2016 12:30:59 Alan Sloan wrote:
> Hi all,
>
> I've been on holiday and discussing gun control with some US gun nuts for
> entertainment.
>
> There are a lot of factors behind the falling crime levels we see all over
> the world, but one of the brighter nuts is insisting the fact that falling
> homicide rates while gun ownership is rising is "evidence" for causation.
> I am insisting that a bivariate in a multivariate situation is not evidence
> of any causation as the 20 or so known reducing factors could be
> outweighing an upward pressure from the increasing gun supply .
>
> Is there a technical term for the various up and down and sideways vectors
> on a single output indicator? The guys legal knowledge is extensive but he
> has poor reasoning skills so I need scientifically correct but
> comprehensible layman's language for him.
>
> And I'm happy to attribute or not any responses, but would like to quote a
> stats qualification if you have one to lend weight to my response.
>
> Any help would be much appreciated.
>
> Alan
>
> On 14 Jul 2016 12:13 a.m., "RADSTATS automatic digest system" <
> [log in to unmask]> wrote:
>
> There is 1 message totaling 51 lines in this issue.
>
> Topics of the day:
>
> 1. Learn R and Data Mining online
>
> ******************************************************
> Please note that if you press the 'Reply' button your
> message will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's
> 'Reply-to-All' button to send your message automatically
> to [log in to unmask]
> Disclaimer: The messages sent to this list are the views of the sender and
> cannot be assumed to be representative of the range of views held by
> subscribers to the Radical Statistics Group. To find out more about Radical
> Statistics and its aims and activities and read current and past issues of
> our newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
>
> ----------------------------------------------------------------------
>
> Date: Wed, 13 Jul 2016 08:06:56 -0700
> From: Geoffrey Hubona <[log in to unmask]>
> Subject: Learn R and Data Mining online
>
> Learn R and Data Mining this summer with 4 permanently-owned,
> certificate-bearing "hands-on" online courses ($10 USD each) taught
> using R software. Navigate links below to register and/or view 2-minute
> video summary and complete information about each course.
>
> Lifetime registration for 1, 2, 3 or all 4 courses, presented below in
> their recommended sequence order. $10 each during July (through July
> 31):
>
> 1) Data Mining with R
> https://www.udemy.com/data-mining-with-r-go-from-beginner-to-advanced/?couponC
> ode=JULY410
> 80 HD video lessons (includes all materials and software)
> 12 hours of video content (not including exercises)
> 2,018 total students
> 4.0/5.0 overall average student evaluation
> 4.1/5.0 recent average student evaluation
>
> 2) More Data Mining with R
> https://www.udemy.com/more-data-mining-with-r/?couponCode=JULY410
> 67 HD video lessons (includes all materials and software)
> 11 hours of video content (not including exercises)
> 1,020 total students
> 3.8/5.0 overall average student evaluation
> 4.1/5.0 recent average student evaluation
>
> 3) Data Mining with Rattle using R
> https://www.udemy.com/data-mining-with-rattle/?couponCode=JULY410
> 82 HD video lessons (includes all materials and software)
> 15 hours of video content (not including exercises)
> 590 total students
> 4.0/5.0 overall average student evaluation
> 4.5/5.0 recent average student evaluation
>
> 4) Case Studies in Data Mining with R
> https://www.udemy.com/case-studies-in-data-mining-with-r/?couponCode=JULY410
> 136 HD video lessons (includes all materials and software)
> 22 hours of video content (not including exercises)
> 931 total students
> 4.4/5.0 overall average student evaluation
> 4.3/5.0 recent average student evaluation
>
> Each course registration includes:
> 1) 24/7 access to video lessons anywhere in the world on any computer,
> laptop, tablet, or smart phone (with Internet connection).
> 2) Downloads of all materials, exercises, software, everything
> 3) Permanent, lifetime ownership of each course.
> 4) Certificate of Completion for each course completed.
> 5) 30-day cancellation/full refund policy, no questions asked.
> 6) All materials, exercises and solutions, all slides, all R scripts you
> see executed in video lessons, all software, everything.
>
>
> ******************************************************
> Please note that if you press the 'Reply' button your
> message will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's
> 'Reply-to-All' button to send your message automatically
> to [log in to unmask]
> Disclaimer: The messages sent to this list are the views of the sender and
> cannot be assumed to be representative of the range of views held by
> subscribers to the Radical Statistics Group. To find out more about Radical
> Statistics and its aims and activities and read current and past issues of
> our newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
>
> ------------------------------
>
> End of RADSTATS Digest - 12 Jul 2016 to 13 Jul 2016 (#2016-99)
> **************************************************************
>
> ******************************************************
> Please note that if you press the 'Reply' button your
> message will go only to the sender of this message.
> If you want to reply to the whole list, use your mailer's
> 'Reply-to-All' button to send your message automatically
> to [log in to unmask]
> Disclaimer: The messages sent to this list are the views of the sender and
> cannot be assumed to be representative of the range of views held by
> subscribers to the Radical Statistics Group. To find out more about Radical
> Statistics and its aims and activities and read current and past issues of
> our newsletter you are invited to visit our web site www.radstats.org.uk.
> *******************************************************
-------------------------------------------------
E-Mail: (Ted Harding) <[log in to unmask]>
Date: 15-Jul-2016 Time: 15:15:54
This message was sent by XFMail
-------------------------------------------------
******************************************************
Please note that if you press the 'Reply' button your
message will go only to the sender of this message.
If you want to reply to the whole list, use your mailer's
'Reply-to-All' button to send your message automatically
to [log in to unmask]
Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
*******************************************************
|