Print

Print


***** To join INSNA, visit http://www.insna.org *****
Dear Ian and others,

To use this option in RSiena where the rate parameter of the actor variable is set to something approximating minus infinity (-100 will do), it will be helpful to use a non-centered dummy variable (1 for M, 0 for F).
For this kind of variable (pregnancy), where a duration / event history model would be appropriate, the model developed in
Greenan, Charlotte C., (2015). Diffusion of Innovations in Dynamic Networks. Journal of the Royal Statistical Society, Series A, 178, 147-166.
DOI: http://dx.doi.org/10.1111/rssa.12054
might be a good idea.
See also section 12.2.4 in the RSiena manual
http://www.stats.ox.ac.uk/~snijders/siena/RSiena_Manual.pdf
This assumes variables that only can go up (diffustion of innovation), but it could also be applied to other variables for which duration modeling is meaningful. Then, however, also the current state (pregnant / non-pregnant) should be used as a predictor for the rate function.

Cheerio,
Tom

=================================
Tom A.B. Snijders
Professor of Statistics and Methodology, Dept of Sociology, University of Groningen
Emeritus Fellow, Nuffield College, University of Oxford
http://www.stats.ox.ac.uk/~snijders

On Sun, Jan 29, 2017 at 10:55 PM, Per Block <[log in to unmask]> wrote:
---------------------- Information from the mail header -----------------------
Sender:       Social Networks Discussion Forum <[log in to unmask]>
Poster:       Per Block <[log in to unmask]>
Subject:      Re: Actor-Oriented Model Question
-------------------------------------------------------------------------------


_____________________________________________________________________ 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.