Computes statistics for the sender activity rate step and receiver choice step in actor-oriented relational event models (e.g., see Stadtfeld & Block, 2017).
Arguments
- reh
an object of class
"remify"characterizing the relational event history.- sender_effects
an object of class
"formula"(or one that can be coerced to that class): a symbolic description of the effects in the sender activity rate step of the actor-oriented model for which statistics are computed, see `Details'- receiver_effects
an object of class
"formula"(or one that can be coerced to that class): a symbolic description of the effects in the receiver choice step of model for which statistics are computed, see `Details'- attr_actors
optionally, an object of class
"data.frame"that contains exogenous attributes for actors (see Details).- attr_dyads
optionally, an object of class
data.frameormatrixcontaining attribute information for dyads (see Details).- method
Specifies the method for managing simultaneous events, i.e., events occurring at the same time. The default 'method' is 'pt' (per timepoint), where statistics are computed once for each unique timepoint in the edgelist. Alternatively, you can choose 'pe' (per event), where statistics are computed once for each unique event observed in the edgelist.
- memory
The memory to be used. See `Details'.
- memory_value
Numeric value indicating the memory parameter. See `Details'.
- start
an optional integer value, specifying the index of the first time or event in the relational event history for which statistics must be computed (see 'Details')
- stop
an optional integer value, specifying the index of the last time or event in the relational event history for which statistics must be computed (see 'Details')
- display_progress
should a progress bar for the computation of the endogenous statistics be shown (TRUE) or not (FALSE)?
- attr_data
deprecated, please use "attr_actors" instead
- attributes
deprecated, please use "attr_data" instead
- edgelist
deprecated, please use "reh" instead
Value
An object of class 'aomstats'. List with in the first element the statistics for the sender activity rate step and in the second element the statistics for the receiver choice step. The 'aomstats' object has the following attributes:
modelType of model that is estimated.
formulaModel formula(s), obtained from the formula(s) inputted to 'sender_effects' and/or 'receiver_effects'.
actorsThe set of actors used to construct the statistics, obtained from the remify object inputted to 'reh'.
Effects
The statistics to be computed are defined symbolically and should be
supplied to the sender_effects and/or receiver_effects
arguments in the form ~ effects. The terms are separated by +
operators. For example: receiver_effects = ~ inertia() + otp().
Interactions between two effects can be included with * or :
operators. For example: receivereffects = ~ inertia():otp(). A list
of available effects can be obtained with actor_effects().
The majority of the statistics can be scaled in some way, see
the documentation of the scaling argument in the separate effect
functions for more information on this.
attr_actors
For the computation of the exogenous statistics an attributes object
with the exogenous covariate information has to be supplied to the
attr_actors argument in either remstats() or in the separate
effect functions supplied to the ..._effects arguments (e.g., see
send). This attr_actors object should be constructed as
follows: A dataframe with rows referring to the attribute value of actor
i at timepoint t. A `name` column is required that contains the
actor name (corresponding to the actor names in the relational event
history). A `time` column is required that contains the time when attributes
change (set to zero if none of the attributes vary over time). Subsequent
columns contain the attributes that are called in the specifications of
exogenous statistics (column name corresponding to the string supplied to
the variable argument in the effect function). Note that the
procedure for the exogenous effects `tie' and `event' deviates from this,
here the exogenous covariate information has to be specified in a different
way, see tie and event.
attr_dyads
For the computation of the dyad exogenous statistics with tie(), an attributes object with the exogenous covariates information per dyad has to be supplied. This is a data.frame or matrix containing attribute information for dyads. If attr_dyads is a data.frame, the first two columns should represent "actor1" and "actor2" (for directed events, "actor1" corresponds to the sender, and "actor2" corresponds to the receiver). Additional columns can represent dyads' exogenous attributes. If attributes vary over time, include a column named "time". If attr_dyads is a matrix, the rows correspond to "actor1", columns to "actor2", and cells contain dyads' exogenous attributes.
Memory
The default `memory` setting is `"full"`, which implies that at each time point $t$ the entire event history before $t$ is included in the computation of the statistics. Alternatively, when `memory` is set to `"window"`, only the past event history within a given time window is considered (see Mulders & Leenders, 2019). This length of this time window is set by the `memory_value` parameter. For example, when `memory_value = 100` and `memory = "window"`, at time point $t$ only the past events that happened at most 100 time units ago are included in the computation of the statistics. A third option is to set `memory` to `"interval"`. In this case, the past event history within a given time interval is considered. For example, when `"memory_value" = c(50, 100)` and `memory = "window"`, at time point $t$ only the past events that happened between 50 and 100 time units ago are included in the computation of the statistics. Finally, the fourth option is to set `memory` to `"decay"`. In this case, the weight of the past event in the computation of the statistics depend on the elapsed time between $t$ and the past event. This weight is determined based on an exponential decay function with half-life parameter `memory_value` (see Brandes et al., 2009).
Event weights
Note that if the relational event history contains a column that is named ``weight'', it is assumed that these affect the endogenous statistics. These affect the computation of all endogenous statistics with a few exceptions that follow logically from their definition (e.g., the recenyContinue statistic does depend on time since the event and not on event weights).
Subset of the relational event history
Optionally, statistics can be computed for a slice of the relational event sequence - but based on the entire history. This is achieved by setting the start and stop values equal to the index of the first and last event for which statistics are requested. For example, start = 5 and stop = 5 computes the statistics for only the 5th event in the relational event sequence, based on the history that consists of events 1-4.
References
Stadtfeld, C., & Block, P. (2017). Interactions, actors, and time: Dynamic network actor models for relational events. Sociological Science, 4, 318–352. doi:10.15195/v4.a14
Examples
library(remstats)
# Load the data
data(history)
data(info)
# Prepare the data
reh <- remify::remify(edgelist = history, model = "actor")
# Define the sender effects
seff <- ~ send("extraversion")
# Define the receiver_effects
reff <- ~ receive("agreeableness") + inertia() + otp()
# Compute the statistics
aomstats(
reh = reh, sender_effects = seff, receiver_effects = reff,
attr_actors = info
)
#> Relational Event Network Statistics
#> > Model: actor-oriented
#> > Computation method: per time point
#> > Sender model:
#> >> Dimensions: 115 time points x 10 actors x 2 statistics
#> >> Statistics:
#> >>> 1: baseline
#> >>> 2: send_extraversion
#> > Receiver model:
#> >> Dimensions: 115 events x 10 actors x 3 statistics
#> >> Statistics:
#> >>> 1: receive_agreeableness
#> >>> 2: inertia
#> >>> 3: otp