***** To join INSNA, visit http://www.insna.org ***** Elena, There exists notions of c-p structure that are just fine for weighted networks (such as two I have helped developed, though only one is written up and publicly available so far), but you seem to have a specific method in mind. As you did not state the method you're using, it's impossible for me to state whether or not _that specific method_ can handle it. ----- Mason > > ---------------------------------------------------------------------- > > Date: Wed, 29 Aug 2012 07:10:27 +0200 > From: Elena Pavan <[log in to unmask]> > Subject: 2mode core-periphery model > > --0016e649863e7fcda404c8609550 > Content-Type: text/plain; charset=ISO-8859-1 > Content-Transfer-Encoding: quoted-printable > > ***** To join INSNA, visit http://www.insna.org ***** > > Hi all, > > does anyone knows what could be the problem if i continue to obtain a 0 > score of fitness in a core-periphery model run on a 2mode network which is > weighted and is done my textual items by speaker? ex. "home" by "speaker > 1"; "a beautiful home" by "speaker 2". To avoid possible problems due to > the use of c-p with weighted networks (is it possible?) I also dichotomized > using different thresholds - to get a good number of 0 thus maintaining > relationships that are plausible for my research questions. > > matrixes i am using are rather small (13x5; 32x5; 115x5; 17x5); but if i > use the davis 2mode dataset on women and events the blockmodelling seems to > work just fine...so there must be something with the data (transposition > did not sort any effect either). > any advice or comment will be appreciated, > > thanks in advance > elena > > --=20 > > Elena Pavan, Ph.D. > Post Doctoral Research Fellow > Dipartimento di Sociologia e Ricerca Sociale > Universit=E0 di Trento > via Verdi 26, 38122 Trento (Italy) > http://www.reactionproject.info > *[log in to unmask]* > tel: +39 0461 28 1378 > Twitter: @reaction_info > ----- Mason _____________________________________________________________________ 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.