***** To join INSNA, visit http://www.sfu.ca/~insna/ *****
Dear 'NETers --
Have any of you conducted (or come across) analyses of networks that rely
on systems of equations to treat both continuous and discrete variables?
I am working to relate spatial segregation (by race) in cities to
individual/houshold traits (race, education, marital status, etc.),
associational indicators (how involved are you with formal groups, informal
socializing, etc.)--and all this to having interracial friendships. The
latter is, unfortunately, a yes/no dichotomous variable.
Seems I can either analyze this as a path (with the network variable as the
end outcome of interest) or, more conservatvely, as a system of
simultaneous equations. Regardless, even the powerful stats packages
popular with econometricians seem limited in their capacity to handle both
continuous and discrete variables in a single system of equations. One
colleague recommended LIMDEP since STATA 8 (issued just last month) doesn't
offer a very adequate handling of this. But perhaps I'm overlooking
something in this picture or alternative software better suited to the math
prob this poses.
Many thanks for any leads -- Xav
Xavier de Souza Briggs
Martin Luther King, Jr. Visiting Professor
MIT Department of Urban Studies and Planning
77 Massachusetts Avenue, Room 9-541
Cambridge, MA 02139, U.S.A.
(voice) 617.253.7956 (fax) 258.8594
"I am not content with a place to sleep.
What I want is a thousand places to dream." (Miro')
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.