Print

Print


*****  To join INSNA, visit http://www.insna.org  *****

Dear Mason and Prosperina,

Thank you very much for the suggestions you provided regarding guide on valued data.  

Best,
Tuugi


-----Original Message-----
From: Social Networks Discussion Forum [mailto:[log in to unmask]] On Behalf Of SOCNET automatic digest system
Sent: Thursday, February 21, 2013 12:00 AM
To: [log in to unmask]
Subject: SOCNET Digest - 19 Feb 2013 to 20 Feb 2013 (#2013-45)

There are 2 messages totalling 349 lines in this issue.

Topics of the day:

  1. Guide for working with valued data (2)

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.

----------------------------------------------------------------------

Date:    Wed, 20 Feb 2013 05:16:18 +0000
From:    Mason Alexander Porter <[log in to unmask]>
Subject: Guide for working with valued data

*****  To join INSNA, visit http://www.insna.org  *****

Tugsjargal,

I'll give a very incomplete but hopefully still helpful answer to your question.

In a recent paper, my collaborators and I needed to consider both weighted and unweighted networks, and we felt it was necessary (i.e., I am extremely pedantic so I insisted) that we tabulate all of the diagnostics we used in that paper in the appendix.  The part that I think you will find helpful is that this includes some discussion and references of generalizations of concepts like betweenness centrality and clustering coefficients for weighted networks.  The paper is here:

 	http://people.maths.ox.ac.uk/~porterm/papers/granular-final.pdf


This paper is on granular networks rather than social networks, so there are obviously many aspects you'll need to consider that we didn't (one gets different types of missing-data biases in granular versus social networks, the granular networks have very special structures, etc), but I think this will still be useful for you at least at the level of a few basic definitions, how to generalize them, and where to look for more info.

So this isn't comprehensive by any stretch of the imagination, but at least for a few of the common measures (and some uncommon ones) it can help.

And that appendix was a royal pain to write, so I really hope others find it useful! :)

-----
Mason

>
>
>
> I would like to know if there is a good resource/ guide/ reference for 
> work= ing with valued data.  I am finding brief mentions of a couple 
> of measures = here and there, but I am looking for a more 
> comprehensive source that talks= about how various SNA measures do or do not work well with valued data, ho=
> w their interpretations change with valued data, potential issues etc.   Ca=
> n you please tell me how/where I could learn more about working with 
> valued= data?


-----
Mason

----------------------------------------------------------------------------
  Mason A. Porter
  University Lecturer (and Tutorial Fellow, Somerville College)
  Oxford Centre for Industrial and Applied Mathematics
  Mathematical Institute, University of Oxford

  Homepage: http://www.maths.ox.ac.uk/~porterm, Skype: tepid451
  Blog: http://masonporter.blogspot.com/
  ----------------------------------------------------------------------------
  "Few things are deadlier than me armed with a red pen." (Me)
  ----------------------------------------------------------------------------

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.

------------------------------

Date:    Wed, 20 Feb 2013 20:06:33 +0100
From:    Maria Prosperina VITALE <[log in to unmask]>
Subject: Re: Guide for working with valued data

--=_4335b5ef9a31956602b06b5345769edb
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset=UTF-8

*****  To join INSNA, visit http://www.insna.org  *****

 

Here some papers that consider valued networks:


http://link.springer.com/article/10.1007%2Fs11135-011-9493-2


http://www2.arnes.si/~aziber4/blockmodeling/Dissertation-final-corrected.pdf


http://toreopsahl.com/2009/04/03/article-clustering-in-weighted-networks/


http://www.ncbi.nlm.nih.gov/pmc/articles/PMC374315/


http://www-personal.umich.edu/~mejn/papers/016132.pdf


http://www.sciencedirect.com/science/article/pii/S0378873307000731


http://arxiv.org/abs/cond-mat/0407503 

BOOK


http://www.amazon.com/Weighted-Network-Analysis-Applications-Genomics/dp/1441988181


Best, 

Prosperina 

Il 20.02.2013 06:16 Mason Alexander Porter ha
scritto: 

> ***** To join INSNA, visit http://www.insna.org *****
> 
>
Tugsjargal,
> 
> I'll give a very incomplete but hopefully still helpful
answer to your 
> question.
> 
> In a recent paper, my collaborators and
I needed to consider both weighted 
> and unweighted networks, and we
felt it was necessary (i.e., I am 
> extremely pedantic so I insisted)
that we tabulate all of the diagnostics 
> we used in that paper in the
appendix. The part that I think you will 
> find helpful is that this
includes some discussion and references of 
> generalizations of
concepts like betweenness centrality and clustering 
> coefficients for
weighted networks. The paper is here:
> 
>
http://people.maths.ox.ac.uk/~porterm/papers/granular-final.pdfThis
paper is on granular networks rather than social networks, so there 
>
are obviously many aspects you'll need to consider that we didn't (one

> gets different types of missing-data biases in granular versus social

> networks, the granular networks have very special structures, etc),
but 
> I think this will still be useful for you at least at the level
of a few 
> basic definitions, how to generalize them, and where to look
for more info.
> 
> So this isn't comprehensive by any stretch of the
imagination, but at 
> least for a few of the common measures (and some
uncommon ones) it can 
> help.
> 
> And that appendix was a royal pain
to write, so I really hope others find 
> it useful! :)
> 
> -----
>
Mason
> 
>> I would like to know if there is a good resource/ guide/
reference for work= ing with valued data. I am finding brief mentions of a couple of measures = here and there, but I am looking for a more comprehensive source that talks= about how various SNA measures do or do not work well with valued data, ho= w their interpretations change with valued data, potential issues etc. Ca= n you please tell me how/where I could learn more about working with valued= data?
> 
> -----
> Mason
>

>
----------------------------------------------------------------------------
>
Mason A. Porter
> University Lecturer (and Tutorial Fellow, Somerville
College)
> Oxford Centre for Industrial and Applied Mathematics
>
Mathematical Institute, University of Oxford
> 
> Homepage:
http://www.maths.ox.ac.uk/~porterm, Skype: tepid451
> Blog:
http://masonporter.blogspot.com/
>
----------------------------------------------------------------------------
>
"Few things are deadlier than me armed with a red pen." (Me)
>
----------------------------------------------------------------------------
>

>
_____________________________________________________________________
>
SOCNET is a service of INSNA, the professional association for social
>
network researchers (http://www.insna.org). To unsubscribe, send
> an
email message to [log in to unmask] containing the line
>
UNSUBSCRIBE SOCNET in the body of the message.


_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.
 
--=_4335b5ef9a31956602b06b5345769edb
Content-Transfer-Encoding: quoted-printable
Content-Type: text/html; charset=UTF-8

*****  To join INSNA, visit http://www.insna.org  ***** <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"> <html><body> <p>&nbsp;</p> <p>Here some papers that consider valued networks:</p> <p>&nbsp;</p> <p>http://link.springer.com/article/10.1007%2Fs11135-011-9493-2</p>
<p>http://www2.arnes.si/~aziber4/blockmodeling/Dissertation-final-corrected=
=2Epdf</p>
<p>http://toreopsahl.com/2009/04/03/article-clustering-in-weighted-networks=
/</p>
<p>http://www.ncbi.nlm.nih.gov/pmc/articles/PMC374315/</p>
<p>http://www-personal.umich.edu/~mejn/papers/016132.pdf</p>
<p>http://www.sciencedirect.com/science/article/pii/S0378873307000731</p>
<p>http://arxiv.org/abs/cond-mat/0407503</p>
<p>BOOK</p>
<p>http://www.amazon.com/Weighted-Network-Analysis-Applications-Genomics/dp=
/1441988181</p>
<p>Best,</p>
<p>Prosperina</p>
<p>Il 20.02.2013 06:16 Mason Alexander Porter ha scritto:</p> <blockquote type=3D"cite" style=3D"padding-left:5px; border-left:#1010ff 2p= x solid; margin-left:5px; width:100%"><!-- html ignored --><!-- head ignore= d --><!-- meta ignored -->
<pre>*****  To join INSNA, visit <a href=3D"http://www.insna.org">http://ww=
w.insna.org</a>  *****

Tugsjargal,

I'll give a very incomplete but hopefully still helpful answer to your=20 question.

In a recent paper, my collaborators and I needed to consider both weighted=
=20
and unweighted networks, and we felt it was necessary (i.e., I am=20 extremely pedantic so I insisted) that we tabulate all of the diagnostics=
=20
we used in that paper in the appendix.  The part that I think you will=20 find helpful is that this includes some discussion and references of=20 generalizations of concepts like betweenness centrality and clustering=20 coefficients for weighted networks.  The paper is here:

 	<a href=3D"http://people.maths.ox.ac.uk/~porterm/papers/granular-final.pd=
f">http://people.maths.ox.ac.uk/~porterm/papers/granular-final.pdf</a>This = paper is on granular networks rather than social networks, so there=20 are obviously many aspects you'll need to consider that we didn't (one=20 gets different types of missing-data biases in granular versus social=20 networks, the granular networks have very special structures, etc), but=20 I think this will still be useful for you at least at the level of a few=20 basic definitions, how to generalize them, and where to look for more info= =2E

So this isn't comprehensive by any stretch of the imagination, but at=20 least for a few of the common measures (and some uncommon ones) it can=20 help.

And that appendix was a royal pain to write, so I really hope others find=
=20
it useful! :)

-----
Mason</pre>
<blockquote type=3D"cite" style=3D"padding-left:5px; border-left:#1010ff 2p= x solid; margin-left:5px; width:100%">I would like to know if there is a go= od resource/ guide/ reference for work=3D ing with valued data. I am findin= g brief mentions of a couple of measures =3D here and there, but I am looki= ng for a more comprehensive source that talks=3D about how various SNA meas= ures do or do not work well with valued data, ho=3D w their interpretations=  change with valued data, potential issues etc. Ca=3D n you please tell me = how/where I could learn more about working with valued=3D data?</blockquote=
>
<pre>
-----
Mason

---------------------------------------------------------------------------=
-
  Mason A. Porter
  University Lecturer (and Tutorial Fellow, Somerville College)
  Oxford Centre for Industrial and Applied Mathematics
  Mathematical Institute, University of Oxford

  Homepage: <a href=3D"http://www.maths.ox.ac.uk/~porterm">http://www.maths=
=2Eox.ac.uk/~porterm</a>, Skype: tepid451
  Blog: <a href=3D"http://masonporter.blogspot.com/">http://masonporter.blo=
gspot.com/</a>
  -------------------------------------------------------------------------=
---
  "Few things are deadlier than me armed with a red pen." (Me)
  -------------------------------------------------------------------------=
---

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social network researchers (<a href=3D"http://www.insna.org">http://www.insna.org<=
/a>). To unsubscribe, send
an email message to <a href=3D"mailto:[log in to unmask]">listserv@list=
s.ufl.edu</a> containing the line
UNSUBSCRIBE SOCNET in the body of the message.
</pre>
</blockquote>
<p>&nbsp;</p>
<div>&nbsp;</div>
</body></html>
_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social network researchers (http://www.insna.org). To unsubscribe, send an email message to [log in to unmask] containing the line UNSUBSCRIBE SOCNET in the body of the message.

--=_4335b5ef9a31956602b06b5345769edb--

------------------------------

End of SOCNET Digest - 19 Feb 2013 to 20 Feb 2013 (#2013-45)
************************************************************

_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.