Print

Print


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

If you have 30,000 nodes in one large component, perhaps you have set the level for "what a link is" too low? --> The Hairball Paradox  ;-)

Don't be afraid to to look at stronger ties that appear within AND between naturally dense clusters, like in this diagram...

http://twitpic.com/35xskx

The picture above was a hairball when we included "all links".  When we filtered for the more frequent and confirmed ties, the above pattern emerged.  Perhaps your data may show something similar if you have some value [frequency/strength/multiplexity/time/etc] and/or direction on your links.  

Valdis Krebs
http://orgnet.com
http://thenetworkthinkers.com


On Dec 14, 2010, at 7:14 AM, T.A.B.SNIJDERS wrote:

> *****  To join INSNA, visit http://www.insna.org  *****
> 
> Dear Zhang Lun,
> 
> It is my personal opinion that in many cases much more can be learned
> from breaking up such a large network into more homogeneous subsets and
> analysing the structure and dynamics of the sub-networks.
> 
> Best wishes,
> 
> Tom
> 
> ?? wrote:
>> ---------------------- Information from the mail header -----------------------
>> Sender:       Social Networks Discussion Forum <[log in to unmask]>
>> Poster:       =?GB2312?B?1cXC1w==?= <[log in to unmask]>
>> Subject:      Questions about modeling the evolution of social network with
>>              over 30,000 nodes
>> -------------------------------------------------------------------------------
>> 
>> --0015175cd2d07d759b04973691a9
>> Content-Type: text/plain; charset=ISO-8859-1
>> 
>> *****  To join INSNA, visit http://www.insna.org  *****
>> 
>> Dear all:
>> I currently have a dataset of an online social network with over 30,000
>> nodes. I want to use the p* model or Snijders' stochastic actor-based model
>> to estimate the evolution of the network. However, the
>> current programs (e.g., SIENA) do not allow the input data larger than 1,000
>> nodes.
>> 
>> Can anyone give me some advices on the model estimation?
>> 
>> Thanks,
>> ZHANG Lun
>> 
>> Dept. Media & Communication,
>> City University of Hong Kong
>> 
>> _____________________________________________________________________
>> 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.
>> 
>> --0015175cd2d07d759b04973691a9
>> Content-Type: text/html; charset=ISO-8859-1
>> Content-Transfer-Encoding: quoted-printable
>> 
>> *****  To join INSNA, visit http://www.insna.org  *****
>> Dear all:=A0<div>I currently have a dataset of an online social network wit=
>> h over 30,000 nodes. I want to use the p* model or Snijders&#39; stochastic=
>> actor-based model to estimate the evolution of the network. However, the c=
>> urrent=A0programs=A0(e.g., SIENA) do not allow the input data larger than 1=
>> ,000 nodes.=A0</div>
>> <div><br></div><div>Can anyone give me some advices on the model estimation=
>> ?=A0</div><div><br></div><div>Thanks,=A0</div><div>ZHANG Lun</div><div><br>=
>> </div><div>Dept. Media &amp; Communication,</div><div>City University of Ho=
>> ng Kong</div>
>> <div><br></div>
>> _____________________________________________________________________
>> 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.
>> 
>> --0015175cd2d07d759b04973691a9--
> 
> -- 
> ================================================
> Tom A.B. Snijders
> Professor of Statistics in the Social Sciences
> University of Oxford
> 
> Professor of Statistics and Methodology
> Department of Sociology, University of Groningen
> 
> for addresses and telephone numbers: see
> http://stat.gamma.rug.nl/snijders/
> 
> _____________________________________________________________________
> 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.