Specifies the statistic for a participation shift AB-XB.
Arguments
- consider_type
logical, indicates whether to consider the event type in determining which dyads create a pshift (TRUE, default) or not (FALSE).
Details
The AB-XB participation shift refers to one of Gibson's (2003) dyadic participation shifts. The AB-XB pshift refers to a tendency for turn usurping (here, the next sender is not in the previous event and the next receiver is the previous receiver). For each timepoint t, the psABXB statistic is equal to one for the dyads that will create the participation shift if they would occur in the edgelist at time t and equal to zero for the dyads that will not create this participation shift. If consider_type is set to TRUE, the type of the AB event and the type of the XB events have to be equal. If it is set to FALSE, the participation shift is set to one for every XB event, regardless of the event type. If multiple events in the edgelist occur at the same time point, the order of these events determines whether the p-shift is observed. Note that the AB-XB pshift is only defined for directed events.
Examples
reh_tie <- remify::remify(history, model = "tie")
effects <- ~ psABXB()
remstats(reh = reh_tie, tie_effects = effects)
#> Relational Event Network Statistics
#> > Model: tie-oriented
#> > Computation method: per time point
#> > Dimensions: 115 time points x 90 dyads x 2 statistics
#> > Statistics:
#> >> 1: baseline
#> >> 2: psABXB