Auxiliaries no longer directly affect whether the model is considered…

… dyad-dependent.
statnet · Feb 2, 2024 · 00c8213 · 00c8213
1 parent 3d07cf5
commit 00c8213
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 3 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,5 +1,5 @@
 Package: ergm
-Version: 4.6-7323
+Version: 4.6-7324
 Date: 2024-02-02
 Title: Fit, Simulate and Diagnose Exponential-Family Models for Networks
 Authors@R: c(

diff --git a/R/is.dyad.independent.R b/R/is.dyad.independent.R
@@ -40,7 +40,8 @@ is.dyad.independent.NULL <- function(object, ...) TRUE # By convention.
 #' @describeIn ergm_model Tests whether the model is dyad-independent.
 #' @export
 is.dyad.independent.ergm_model <- function(object, ...){
-  ! any(sapply(object$terms, function(term) is.null(term$dependence) || term$dependence))
+  ## NB: Auxiliaries (i.e., terms without statistics) do not affect dyadic dependence.
+  ! any(sapply(object$terms, function(term) length(term$coef.name) && (is.null(term$dependence) || term$dependence)))
 }
 
 #' @rdname is.dyad.independent

diff --git a/vignettes/Terms-API.Rmd b/vignettes/Terms-API.Rmd
@@ -129,7 +129,7 @@ In the following, let $p = \dim(\eta) = \dim(g(y))$, the dimension of the statis
 
 `pkgname`: a string containing the name of the `R` package containing the `C` implementation; if not specified, the package in which the `Init*ErgmTerm.*` function was found is assumed.
 
-`dependence`: a logical value indicating whether the addition of this term to the model induces dyadic-dependence; if all terms have `dependence` set to `FALSE`, the model is inferred to be dyad-independent; if not specified, `TRUE` is assumed.
+`dependence`: a logical value indicating whether the addition of this term to the model induces dyadic-dependence; if all terms (ignoring auxiliaries) have `dependence` set to `FALSE`, the model is inferred to be dyad-independent; if not specified, `TRUE` is assumed.
 
 `emptynwstats`: a numeric vector of length $p$ providing the value of the statistic if evaluated on an empty network; if not specified or NULL, assumed to be a vector of zeros. (See `InitErgmTerm.degree()` in `R/InitEergmTerm.R` for an example.)