[Rsiena-help] Interacting two effects in models of multiple networks

[Tom Snijders]

Dear Bob,

(By the way: for this type of question, the Siena-Stocnet list
http://groups.yahoo.com/groups/stocnet/
is more appropriate).
I think that, depending on directionality, the effects from, sharedIn, closure, or fromMutual might be appropriate. (Note: this is not an interaction, it’s a regular effect).

Best regards,
Tom

=================================================
Tom A.B. Snijders
Professor of Statistics and Methodology
Department of Sociology, University of Groningen
Emeritus Fellow, Nuffield College, University of Oxford
Associate Member, Dept. of Statistics, University of Oxford

From: rsiena-help-bounces at lists.r-forge.r-project.org [mailto:rsiena-help-bounces at lists.r-forge.r-project.org] On Behalf Of Bob Faris
Sent: 04 January 2018 19:11
To: rsiena-help at lists.r-forge.r-project.org
Subject: [Rsiena-help] Interacting two effects in models of multiple networks

Hi all, I am estimating RSiena models of multiple (binary, one-mode, two-wave) networks and have a significant positive effect from a tie in the W network (allegiance) to a tie in the X (exports) network (the "crprod" effect). What I'd like to test is an interaction between shared W partners (something like gwespFBMix) and the direct W tie on the X tie--in other words, does allegiance (W) lead to exports (X) more often when there are more shared allies?

Here's the script, thanks in advance!
-Bob


exports <- sienaNet(array(c(exports1978,exports1979), dim=c(91,91,2)))

ally  <- sienaNet(array(c(ally1978,ally1979), dim=c(91,91,2)))



data.1978 <- sienaDataCreate(exports,ally)

effects.1978 <- getEffects(data.1978)

effects.1978 <- includeEffects(effects.1978,transTrip,cycle3,

                              inPopSqrt,outActSqrt,inActSqrt,name="exports")

effects.1978 <- includeEffects(effects.1978,transTrip,cycle3,

                              inPopSqrt,outActSqrt,inActSqrt,name="ally")

effects.1978 <- includeEffects(effects.1978,crprod,name="ally",interaction1="exports")

effects.1978 <- includeEffects(effects.1978,crprod,name="exports",interaction1="ally")

effects.1978 <- includeEffects(effects.1978,crprodRecip,name="ally",interaction1="exports")

effects.1978 <- includeEffects(effects.1978,crprodRecip,name="exports",interaction1="ally")

effects.1978 <- includeEffects(effects.1978,gwespFBMix,name="ally",interaction1="exports")

effects.1978 <- includeEffects(effects.1978,gwespFBMix,name="exports",interaction1="ally")

effects.1978

Alg.1978 <- sienaAlgorithmCreate(projname = 'net1978', seed=123 )

ans.1978 <- siena07(Alg.1978, data = data.1978, effects = effects.1978)
ans.1978








************************************
Robert Faris, PhD
Associate Professor
Department of Sociology
University of California at Davis
2247 Social Sciences and Humanities
One Shields Avenue
Davis, CA 95616
Cell:  510-221-8876
Fax 530-752-0783
http://sociology.ucdavis.edu/people/rwfaris
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.r-forge.r-project.org/pipermail/rsiena-help/attachments/20180105/aa84c886/attachment-0001.html>