ERGM crashes when fitting MCMC: "Error in T2nullity && verbose : invalid 'x' type in 'x && y'"

[matwurst]

Dear all,

I will keep it short since it's late at night, but every time my models start to fit the model, it crashes with the following error:

Iteration 16 of at most 60:
Optimizing with step length 1.0000.
The log-likelihood improved by 0.0826.
Error in T2nullity && verbose : invalid 'x' type in 'x && y'

anyone has an idea where this comes from?

This is my code:

model <- ergm(mixed.recht ~ edges + +gwesp(0.25,fixed=T) + nodefactor("var1") + ...)

[mbojan]

This seems to be, roughly speaking, a numerical problem in the estimation. It is hard to say whether we have a problem with the software or something is wrong with your data, or the model specification vis a vis your data. We'd need a reproducible example, can you provide one?

[matwurst]

Dear mbojan, can be closed. I updated the ERMG-package and found that one covar semed to have crashed the code.

[cbccbcc]

I encountered the same issue but a slightly different one. When I was coding like:

gw1_sup <- ergm(supnet ~ edges + nodefactor("edu") + nodefactor("income") + 
nodefactor("work") +  nodefactor("religious") + nodefactor("gender") + nodecov("age") + 
edgecov(kin_sup,"kinweight") + gwidegree(.1, T) + gwesp(.1, T) + gwdsp(.1, T), 
control = control.ergm(MCMC.samplesize = 1e+5, MCMC.burnin = 1e+6, MCMC.interval = 1000, seed = 567), 
eval.loglik = T, verbose = T)

everything is okay. But when I turned the "edu" and "income" to continuous variables and code like:

gw1_sup <- ergm(supnet ~ edges + nodefactor("work") +  nodefactor("religious") + 
nodefactor("gender") + +nodecov("edu") + nodecov("income") + nodecov("age") + 
edgecov(kin_sup,"kinweight") + gwidegree(.1, T) + gwesp(.1, T) + gwdsp(.1, T), 
control = control.ergm(MCMC.samplesize = 1e+5, MCMC.burnin = 1e+6, MCMC.interval = 1000, seed = 567), 
eval.loglik = T, verbose = T) )

, at first it went okay but at around 8/9 iteration the ergm collapsed and report the same error in this issue. I don't know why :(

[xxhandup]

Dear matwurst, May I ask how you solved it? Just updated ergm's package? Have other matching packages been updated? Which version has it been updated to? Thank you very much

[cbccbcc]

If I recall right, I used "ergm.tapered" instead of "ergm" and solve it, maybe updating the package would help )

[xxhandup]

Thank your reply. I will try it.