Off topic - scatter plots

[Stephen Hampshire-2]

Hi all,

I hope you'll forgive the offtopic posting, but my Googling is letting me
down.

Some years ago I came across some nice little data sets that illustrated how
variables could have identical descriptive statistics and identical linear
relationships, yet when plotted in a scatter graph had obviously different
true relationships (one was linear, one was probably quadratic etc).

Can anyone point me to a reference for the data? I've tried creating some
myself, and it's difficult to come up with anything as neat as this example
was.

Thanks,

Stephen

[Mike P-5]

I think your probably looking for Anscombe's Quartet stuff

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Stephen Hampshire
Sent: 04 January 2007 14:56
To: [hidden email]
Subject: Off topic - scatter plots

Hi all,

I hope you'll forgive the offtopic posting, but my Googling is letting
me down.

Some years ago I came across some nice little data sets that illustrated
how variables could have identical descriptive statistics and identical
linear relationships, yet when plotted in a scatter graph had obviously
different true relationships (one was linear, one was probably quadratic
etc).

Can anyone point me to a reference for the data? I've tried creating
some myself, and it's difficult to come up with anything as neat as this
example was.

Thanks,

Stephen

________________________________________________________________________
This e-mail has been scanned for all viruses by Star. The service is
powered by MessageLabs. For more information on a proactive anti-virus
service working around the clock, around the globe, visit:
http://www.star.net.uk
________________________________________________________________________

______________________________________________________________________
This email has been scanned by the MessageLabs Email Security System.
For more information please visit http://www.messagelabs.com/email
______________________________________________________________________

[Stephen Hampshire-2]

Exactly right - thanks very much Michael!

> -----Original Message-----
> From: Michael Pearmain [mailto:[hidden email]]
> Sent: 04 January 2007 16:00
> To: Stephen Hampshire; [hidden email]
> Subject: RE: Off topic - scatter plots
>
>
> I think your probably looking for Anscombe's Quartet stuff
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> Stephen Hampshire
> Sent: 04 January 2007 14:56
> To: [hidden email]
> Subject: Off topic - scatter plots
>
> Hi all,
>
> I hope you'll forgive the offtopic posting, but my Googling is letting
> me down.
>
> Some years ago I came across some nice little data sets that illustrated
> how variables could have identical descriptive statistics and identical
> linear relationships, yet when plotted in a scatter graph had obviously
> different true relationships (one was linear, one was probably quadratic
> etc).
>
> Can anyone point me to a reference for the data? I've tried creating
> some myself, and it's difficult to come up with anything as neat as this
> example was.
>
> Thanks,
>
> Stephen
>
> ________________________________________________________________________
> This e-mail has been scanned for all viruses by Star. The service is
> powered by MessageLabs. For more information on a proactive anti-virus
> service working around the clock, around the globe, visit:
> http://www.star.net.uk
> ________________________________________________________________________
>
> ______________________________________________________________________
> This email has been scanned by the MessageLabs Email Security System.
> For more information please visit http://www.messagelabs.com/email
> ______________________________________________________________________

[Anthony Babinec]

Here's a link to the anscombe data

http://exploringdata.cqu.edu.au/anscomb2.htm



-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Stephen Hampshire
Sent: Thursday, January 04, 2007 8:56 AM
To: [hidden email]
Subject: Off topic - scatter plots

Hi all,

I hope you'll forgive the offtopic posting, but my Googling is letting me
down.

Some years ago I came across some nice little data sets that illustrated how
variables could have identical descriptive statistics and identical linear
relationships, yet when plotted in a scatter graph had obviously different
true relationships (one was linear, one was probably quadratic etc).

Can anyone point me to a reference for the data? I've tried creating some
myself, and it's difficult to come up with anything as neat as this example
was.

Thanks,

Stephen

[Daniel Robertson]

The reference to the original article (w/ data) is:

Anscombe, F. J. (1973, Feb). Graphs in Statistical Analysis. The
American Statistician, 27(1), 17-21.

JSTOR Stable URL:
http://links.jstor.org/sici?sici=0003-1305%28196102%2915%3A1%3C21%3ABS%3E2.0.CO%3B2-U


Stephen Hampshire wrote:

> Hi all,
>
> I hope you'll forgive the offtopic posting, but my Googling is letting me
> down.
>
> Some years ago I came across some nice little data sets that illustrated how
> variables could have identical descriptive statistics and identical linear
> relationships, yet when plotted in a scatter graph had obviously different
> true relationships (one was linear, one was probably quadratic etc).
>
> Can anyone point me to a reference for the data? I've tried creating some
> myself, and it's difficult to come up with anything as neat as this example
> was.
>
> Thanks,
>
> Stephen
>
>

--
Daniel Robertson
Sr. Research and Planning Associate
Institutional Research and Planning
Cornell University
440 Day Hall, Ithaca NY 14853-2801
ph:607.255.9642 / irp.cornell.edu

[Rimmer, Tony]

Stephen:

The earlier response gave you the correct reference to Anscombe's 1973
graphing piece but it offered an incorrect JSTOR URL.

The correct JSTOR URL is:
http://links.jstor.org/sici?sici=0003-1305%28197302%2927%3A1%3C17%3AGISA
%3E2.0.CO%3B2-J

The URL offered earlier directs us to a 1961 Anscombe piece on Bayesian
statistics -- all good stuff, nevertheless

Regards
Tony

Tony Rimmer
Director, Faculty Development Center
Cal State Fullerton
Fullerton, CA 92834
714-278-5628
[hidden email]

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Daniel Robertson
Sent: Thursday, January 04, 2007 9:50 AM
To: [hidden email]
Subject: Re: Off topic - scatter plots

The reference to the original article (w/ data) is:

Anscombe, F. J. (1973, Feb). Graphs in Statistical Analysis. The
American Statistician, 27(1), 17-21.

JSTOR Stable URL:
<a href="http://links.jstor.org/sici?sici=0003-1305%28196102%2915%3A1%3C21%3ABS%3">http://links.jstor.org/sici?sici=0003-1305%28196102%2915%3A1%3C21%3ABS%3
E2.0.CO%3B2-U


Stephen Hampshire wrote:
> Hi all,
>
> I hope you'll forgive the offtopic posting, but my Googling is letting
me
> down.
>
> Some years ago I came across some nice little data sets that
illustrated how
> variables could have identical descriptive statistics and identical
linear
> relationships, yet when plotted in a scatter graph had obviously
different
> true relationships (one was linear, one was probably quadratic etc).
>
> Can anyone point me to a reference for the data? I've tried creating
some
> myself, and it's difficult to come up with anything as neat as this
example
> was.
>
> Thanks,
>
> Stephen
>
>

--
Daniel Robertson
Sr. Research and Planning Associate
Institutional Research and Planning
Cornell University
440 Day Hall, Ithaca NY 14853-2801
ph:607.255.9642 / irp.cornell.edu