Print

Print


*****  To join INSNA, visit http://www.sfu.ca/~insna/  *****

I see the points of Dr. Borgatti and Morris. However, I would say that the figuration of network based on attribute data can be meaningful, if we do not acknowledge that they are "real" relationships.

Strictly, we cannot say that "man" vs. "woman" is not a relationship. But, this kind of grouping (men and women) sometimes help us pin down segments of a larger population. For example, if I have a data set about people's TV watching behavior (measuring specific kind of their behavior such as number hours of TV watching or specific time slot (7-9 pm for example) that the survey participant watched TV), I would be able to obtain groups based on their TV watching behavior. Then, I would assess the relatinships with these groups and individuals' other attributes data -- any kinds of "usual suspects (education, socio-econ status, etc.)" -- to see what kinds of attributes and how much do they contribute to their behavioral patterns.*** Or, the data (groups) can be used with other "relational" network data to see how actors' realtions (relational network data) contribute to TV watching behavior.

In this case, even though the network analysis method did not deal with "R"elations; it provided some sort of scheme to see the reality of TV watching behavior.

*** Conventional R-factor analysis would result in the same kinds of result.

Just my opinion...

-hyo at SCILS, Rutgers



----- Original Message -----
From: "Carl Nordlund" <[log in to unmask]>
To: <[log in to unmask]>
Sent: Monday, October 14, 2002 11:48 AM
Subject: SV: Structural data based on actor attributes


> *****  To join INSNA, visit http://www.sfu.ca/~insna/  *****
>
> Thank you for your responses. Also, excuse me for bombarding this mailing
> list with perhaps rudimentary questions but I have noone in my local
> surrounding working with SNA!
>
> Also, I must add that Taylor's approach to generating structural data have
> more elements to it (although still based on evalutation on actor
> attributes), and he also uses a different syntax (see Research Bulletin 23
> and 43, available at http://www.lboro.ac.uk/gawc/publicat.html). I must also
> add that I don't know if another methodology is used in other GaWC papers
> that I haven'r read (so far).
>
> I am glad that I came to the same conclusion: that this isn't network
> analysis done proper!
>
> Yours,
> Carl
>
>
> -----Ursprungligt meddelande-----
> Fran: Social Networks Discussion Forum [mailto:[log in to unmask]]For
> Martina Morris
> Skickat: den 14 oktober 2002 17:35
> Till: [log in to unmask]
> Amne: Re: Structural data based on actor attributes
>
>
> *****  To join INSNA, visit http://www.sfu.ca/~insna/  *****
>
> if the model were { O(i) * O(j) } / O
>
> you would have the beginnings of the classic model for independence (seen
> in the chi-square test and the loglinear model for independence).
> departures from independence can also be modeled in the loglinear
> framework.  networkers often these models for local (egocentric) data
> analysis.
>
> pairing based on attributes is a traditional network interest, but with
> this type of influence the dyads remain independent.  in that sense, it is
> not like most network modeling.
>
> best,
> Martina
>
>
> On Mon, 14 Oct 2002, Carl Nordlund wrote:
>
> > *****  To join INSNA, visit http://www.sfu.ca/~insna/  *****
> >
> > Dear all,
> >
> > When studying the 'World City Network', Peter Taylor has specified a
> > technique for obtaining structural data which is based on actor attributes
> > (Research bulletin 23, GaWC, also published in Geographical Analysis
> 33(2),
> > 2001). He uses a formula like this one:
> >
> > C(i,j) = O(i) * O(j)
> >
> > ...where C(i,j) is the total connectivity between actor i and j and where
> > O(i) and O(j) are total number of TNC offices of actor i respectively j.
> >
> > In short, what is done here is an estimation of the structural value
> between
> > dyads based on internal attributes of the actors. If city i has 2 offices
> > and city j has 3 offices, the structural connectivity value between i and
> j
> > is set to 6, thus implying the total number of links between these two
> > actors.
> >
> > Is this a common way of fetching structural data, i.e to use actor
> > attributes like this? Intuitively, what regards Taylor's study, it feels
> > like a reasonable good approximation of the structural data but when it is
> > only based on actor-internal attributes, I also get the feeling that it
> > isn't following a very 'networkish' style!
> >
> > Yours,
> > Carl
> > -----
> > Carl Nordlund, BA, PhD student
> > carl.nordlund(at)humecol.lu.se
> > Human Ecology Division
> > www.humecol.lu.se
> >
> > _____________________________________________________________________
> > SOCNET is a service of INSNA, the professional association for social
> > network researchers (http://www.sfu.ca/~insna/). To unsubscribe, send
> > an email message to [log in to unmask] containing the line
> > UNSUBSCRIBE SOCNET in the body of the message.
> >
>
> ****************************************************************
>  Blumstein-Jordan Professor of Sociology and Statistics
>  Department of Sociology
>  Box 353340
>  University of Washington
>  Seattle, WA 98195-3340
>
> Phone Numbers:
>  Office:        (206) 685-3402
>  Dept Office:   (206) 543-5882
>  Fax:           (206) 616-2093
>
> email:  [log in to unmask]
>
> _____________________________________________________________________
> SOCNET is a service of INSNA, the professional association for social
> network researchers (http://www.sfu.ca/~insna/). 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.sfu.ca/~insna/). 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.sfu.ca/~insna/). To unsubscribe, send
an email message to [log in to unmask] containing the line
UNSUBSCRIBE SOCNET in the body of the message.