varDyadCovar function

Function to create a changing dyadic covariate object.

This function creates a changing dyadic covariate object from an array.

varDyadCovar(val, centered=TRUE, nodeSets=c("Actors", "Actors"),
     warn=TRUE, sparse=is.list(val), type=c("oneMode", "bipartite"))

Arguments

• val: Array of covariate values, third dimension is the time. Alternatively, a list of sparse matrices of type "TsparseMatrix".
• centered: Boolean: if TRUE, then the overall mean value is subtracted.
• nodeSets: Names (character string) of the associated node sets. If the entire data set contains more than one node set, then the node sets must be specified in all data objects.
• warn: Logical: is a warning given if, for non-sparse input, all values are NA, or all non-missing values are the same.
• sparse: Boolean: whether sparse matrices or not.
• type: oneMode or bipartite: whether the matrix refers to a one-mode or a bipartite (two-mode) network.

Details

When part of a Siena data object, the covariate is assumed to be associated with the node sets named NodeSets

of the Siena data object. The names of the associated node sets will only be checked when the Siena data object is created. In practice, the node set needs to be specified only in the case of the use of the covariate with a two-mode network.

The value of the changing covariate for wave m is supposed in the simulations to be valid in the whole period from wave m

to wave m+1. If the data set has M waves, this means that the values, if any, for wave M will not be used. Therefore, the number of columns can be M or M-1; if the former, the values in the last column will not be used.

Returns

Returns the covariate as an object of class "varDyadCovar", in which form it can be used as an argument to SienaDataCreate.

References

See https://www.stats.ox.ac.uk/~snijders/siena/

Author(s)

Ruth Ripley

See Also

sienaDataCreate, coDyadCovar, coCovar, varCovar, sienaNodeSet

Examples

mydyadvar <- varDyadCovar(array(c(s501, s502), dim=c(50, 50, 2)))