Pavel N. Krivitsky

Right now, `simulate.tergm()` always attempts to run the temporal process forward. However, for GOF and other purposes, we may want to simulate what the networks in the time series "could...

`predict.ergm()` probably won't quite accomplish what the user expects.

EGMME is slow, but testing the package shouldn't take 40 minutes.

One way to resolve the dispatching issue including https://github.com/statnet/tergm/issues/25, and simplify the code in dispatching `simulate_formula` is by requiring the user to wrap LHS in something like `Dynamic()` which will...

For dyad-independent subterms, `MeanAge(~...)` would effectively use their change statistics as weights for computing the mean age.

E.g., ```r nw ~ Diss(~edges+AgeInterval(~edges, from=5, to=10)) ``` would be equivalent to ```r nw ~ Diss(~edges+edges.ageinterval(from=5, to=10)) ``` but would allow arbitrary models to be evaluated on a network constructed...

Shorter name for NodematchFilter()?

10

In light of https://github.com/statnet/ergm/issues/478, `NodematchFilter()` operator, which I had originally put together to test the API, may be worth making more prominent, and that might involve renaming it to something...

Terms affected by `gw.cutoff` should raise an immediate error if they are ever passed a network that exceeds it.

1

For dense networks, they silently return incorrect results that may be mysterious to some users (#484). It should be reasonably safe to simply have the relevant `c_` functions return an...

Implement a generalisation for nodematch() that tests if the two nodes have any attributes or properties in common or counts them?

2

# Term description This stems from [this question on Stack Overflow](https://stackoverflow.com/questions/68070465/homophily-across-two-attributes-with-nodematch-in-r-package-ergm): generalising it, suppose that each node `i` has some *set* `A[i]` of *properties* (I am avoiding "attributes", since we...

In ergm(), rename TARGET_STATS to something more aesthetic and less likely to be used as a variable name?

13

Right now, if `ergm()` is given `target.stats=`, it runs `san()` to obtain the LHS network, calls it `TARGET_STATS`, then replaces the LHS of the model formula with `TARGET_STATS` (the name),...