***** To join INSNA, visit http://www.insna.org *****
Dear Ubaldo,
I think the first thing you should do is to write out the regression
equation that specifies how the individual-level response variable
should depend on the explanatory variables, including the dyadic ones.
That is not trivial and will require some thinking, but it is a modeling
decision that you can only make yourself!
Best wishes,
Tom
Ubaldo Macchitella wrote:
> ---------------------- Information from the mail header -----------------------
> Sender: Social Networks Discussion Forum <[log in to unmask]>
> Poster: Ubaldo Macchitella <[log in to unmask]>
> Subject: Multilvevel models and Social networks
> -------------------------------------------------------------------------------
>
> ***** To join INSNA, visit http://www.insna.org *****
>
> Hi all,
> I am a new member of SOCNET. I am asking your help because I am trying to
> develop e mulitilevel model in which I have:
>
> - An INDIVIDUAL-level response variable
> - Individual, relation(dyadic) and group level explanatory variables.
>
> I saw on Snijders and Bosker's book (1999), at chapter 11, that it is possible
> to build up a multilevel model (on the three levels: single relation, dyad and
> group) having a response variable at the RELATION level. In the way Snijders
> and Bosker suggest, it is possible to manage the sender and receiver effect.
> Would it be possible, conceptually and technically, to do the same having an
> INDIVIDUAL level response variable?
>
> Many thanks,
>
> Ubaldo.
>
> Ubaldo Macchitella
> Istituto di Organizzazione e Sistemi Informativi
> Università commerciale L. Bocconi
> Viale Isonzo, 23
> 20135 Milano
> Tel.: 02/58362578
>
> _____________________________________________________________________
> 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.
--
Tom A.B. Snijders
Professor of Statistics and Methodology
Scientific Director, ICS
Department of Sociology, University of Groningen
Grote Rozenstraat 31
9712 TG Groningen
The Netherlands
+31-(0)50-3636188/6216
http://stat.gamma.rug.nl/snijders/
Note: new email address: [log in to unmask]
_____________________________________________________________________
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.
|