ergm | Diagnose Exponential-Family Models

I am trying to run an exponential random graph model (ergm) on a weighted network (network_ex). This network shows the interactions between individuals in four different groups. Interactions between groups cannot occur so a blockdiagonal constraint needs to be included in the model. However when I include the blockdiagonal constraint the ergm function (that runs otherwise) returns an error (see below) and my R session either runs indefinitely or abort directly.

Is there a way to run an ergm based on a weighted block diagonal matrix?

I'm loading in the florentine dataset using the code below and trying to visualise the network:

I'm trying this code to regenerate this function to plot a network based on this link work, I know some functions are deprecated, I replaced opts with theme, but I got error with theme_rect

In the ergm and latentnet packages, they allow us to input a network and specify covariates. Then, we can add in effects like homophily and clustering (in the latentnet package). It seems there are two branches of applications here:

1) Have existing data/network, and want to see how it performs and how much homophily, clustering exists.

2) Do NOT have existing data, and want to generate from scratch a network that has enough homophily and clustering to our liking.

All of the examples in the above packages work with an existing dataset, samplike, which is the Sampson Monk Data. In the case that I am solely interested in generating a network with a given amount of homophily and clustering, what is the input network I should put in? For example, from code adapted:

I am estimating networks with ERGMs using the statnet suite in R. I would like to visualize the network using the igraph package with size by degree centrality and node color by leadership position. For explanation: it's a shared leadership network and I want to visualize whether an individual has a formal leadership position (LSPosition = 1), visualized in black, or not (LSPosition = 0), visualized in white.

This is my code up to now (graphExample is my network, Data_Axample is an actor attribute data set):

I'm using the ergm R package to try to find out whether individuals from certain groups are more (or less) likely to form a tie (to interact, in this particular case).

I'm having trouble interpreting the output. In particular, when I use an ergm-term, e.g., nodefactor(), what is estimated (if I understand correctly) is the log odds of any tie (i.e., sending or receiving) involving each level of the factor.

For nodemix(), though, when I don't specify which particular node factor pairings should be included and so all are, there seems to be an order, i.e. a term for the pairing that includes both the Teacher and Administration ties (i.e., mix.profile_code.Teacher.Administration as well as those that include the Administration and Teacher ties (mix.profile_code.Administration.Teacher.

My questions:

• does sender/receiver status not matter for nodefactor()? Is there a way to specify nodefactor() for sender and receiver seperately?
• for nodemix(), does the order matter, with the first value in the pair representing the sender, and the second the receiver (i.e., formix.profile_code.Teacher.Administration`, Teacher is the sender, and Administration receiver?

I am currently trying to convert a network object to an igraph object. From various posts, I understand the intergraph package can do this through the asIgraph() function. I am trying to convert the classic Sampson dataset, which is found in the ergm package. When I do:

I would like to simulate exponential family random graphs, and I just started learning to use the statnet and ergm R packages. From the tutorial I found online, I am able to learn an ERGM model from an example dataset:

I would like to provide more than one graph as input to the equiv.clust function in the sna package. For example