[Rsiena-help] clarification on changelog for RSienaTest rev.93
Ruth M. Ripley
ruth at stats.ox.ac.uk
Tue Jun 8 12:27:03 CEST 2010
I noticed that some of the code to deal with composition change in
bipartite networks is missing, so I added the error message to alert
users. I had not heard of any problems, but it is probably not obvious
that the code is incomplete.
If you have missing values with sparse _format_ networks I would have
expected the code to be very slow. (I fixed the one-mode sparse missings
recently because the method was hopelessly slow with a significant number
of missing data, and I was working with such a network.) (If it worked,
this part would be OK, I think.)
I will try to deal with this asap, as soon as I have investigated the
dyadic covariates from yesterday's messages!
On Tue, 8 Jun 2010, marco tonellato wrote:
> Dear Ruth,
> I just read the changelog for RSienaTest rev.93 (04.06.2010), and I saw
> those messages:
> "Using composition change with bipartite networks will give an error message
> ? until this is corrected". And "Bug fix to treatment of missing data in
> sparse format bipartite networks".
> Since I'm actually using sparse bipartite networks with composition change
> (RSiena rev.92) I was wondering whether the problem was there before and you
> fixed it or whether the problem wasn't there before and you signaled it.
> Can you please elaborate on that?
> Thanks. Regards,
More information about the Rsiena-help