Specifies the statistic for a "maximum" effect in the tie-oriented model. A "maximum" effect refers to an exogenous actor attribute that affects dyad (i,j)'s rate of interacting based on the maximum of the values of actors i and j on this attribute.
Usage
maximum(variable, attr_actors = NULL, scaling = c("none", "std"), attr_data)Arguments
- variable
string with the name of the column in the
attr_actorsobject for which the statistic has to be computed.- attr_actors
optionally, an object of class
data.framethat contains the attribute, see 'Details.'- scaling
the method for scaling the statistic. Default is to not scale the statistic. Alternatively, standardization of the statistic per time point can be requested with "std".
- attr_data
Deprecated argument. Please use 'attr_actors' instead.
Details
The statistic at timepoint t for dyad (i,j) is equal to the maximum of the values of actor i and j on the attribute at timepoint t.
Construct the `attr_actors` object as a data frame where each row represents the attribute value of actor i at timepoint t:
name: The actors' name.
time: The time when the attribute values change.
variable: The third column contains the attribute used in the specification of the "difference" effect. The column name should correspond to the string supplied to the
variableargument in the `difference()` function.
Note that it is possible to omit the `attr_actors` object in the call of
difference() and, instead, supply it in the call of remstats()
for multiple exogenous effects.
Examples
reh_tie <- remify::remify(history, model = "tie", directed = FALSE)
effects <- ~ maximum("extraversion")
remstats(reh = reh_tie, tie_effects = effects, attr_actors = info)
#> Relational Event Network Statistics
#> > Model: tie-oriented
#> > Computation method: per time point
#> > Dimensions: 115 time points x 45 dyads x 2 statistics
#> > Statistics:
#> >> 1: baseline
#> >> 2: maximum_extraversion