Risk set


This vignette provides a definition of full, active and manual risk set, it explains how a manual risk set is declared in the processing function remify::remify(), and it shows how the processed risk set looks like in the remify object.


Consider the remify object for the network randomREHsmall.

library(remify) # loading package
data(randomREHsmall) # data

# processing the edgelist 
reh <- remify(edgelist = randomREHsmall$edgelist,
                          directed = TRUE, # events are directed
                          ordinal = FALSE, # model with waiting times
                          model = "tie", # tie-oriented modeling   
                          actors = randomREHsmall$actors,
                          origin = randomREHsmall$origin,
                          omit_dyad = NULL)

# summary(reh)                                

{.tabset .tabset-fade .tabset-pills .tabcontent}

Definition of risk set

A relational event history consists of a time-ordered sequence of (directed or undirected) interaction. For each event, we know:

For instance, the first five events of the randomREHsmall sequence are reported as follows

randomREHsmall$edgelist[1:5,]

where time, actor1, actor2 describe each observed event in the sequence (Note that in this example the type of events is not annotated).

When modeling a relational event sequence, we have to define per each time point a risk set, which consists of the set of those relational events (dyads) that at a specific time point were likely to be observed (this set also contains the event that is actually observed at a specific time point). The definition of the risk set is an important building block of the likelihood function for both tie-oriented and actor-oriented modeling framework. In the sections of this vignette, we discuss three possible definitions of the risk set: full, active and manual risk set. These three types of risk set can be processed with remify::remify() by specifying the risk set type to the input argument riskset.


The full risk set

The most common definition of the risk set assumes that all the possible dyads are likely to occur over the whole observation period. We refer to this definition as full risk set. If the network has N actors and it consists of directed events that can assume a number of C possible event types, then the risk set will be characterized by all the possible directed dyads among N actors, which are D = N(N-1)C, or D = N(N-1)C/2 in the case of undirected dyads. For instance, in the random network (randomREHsmall) dyads are directed, actors are N = 5 and event types are C = 1, therefore we expect the dimension of the risk set to be D = 5 * 4 * 1 = 20. The first five dyads in the full risk set will be

# method getDyad(), see more in ?remify::getDyad
getDyad(x = reh, dyadID = c(1:5)) 

The ID of the dyads (dyadID) corresponds to the order of the dyads used by the functions in ` and it is processed by the functionremify::remify()`. The ID of the dyads is defined by a two-steps approach:

  1. Actors' and types' names are first sorted according to their
    alphanumeric

    The alphanumeric order follows first the order of numbers from 0 to 9, then the alphabetical order of the letters.

    For instance, given the vector of names c("user22","0usr","1user","1deer"), its alphanumeric order will be c("0usr","1deer","1user","user22)

    order, that for the actors in the random network will be,
# sorted vector of actors' names
sorted_actors <- sort(randomREHsmall$actors)
sorted_actors

# number of actors in the network
N <- length(randomREHsmall$actors)

and for the event type will be

# no event type, we set it to an empty string
sorted_types <- c(" ") 

# C = 1 for 'randomREHsmall'
C <- length(sorted_types) 

In this phase, the processing function remify::remify() will also assign numeric IDs to both actors and event types

# IDs of actors will consist of an integer number from 1 to N
names(sorted_actors) <- 1:N
sorted_actors

# IDs of types will be an integer number from 1 to C
names(sorted_types) <- 1:C # in this case is one (artificial) event type
sorted_types
  1. dyads are defined by the triple c(actor1,actor2,type) that is found by looping first on actor2, then actor1, and finally type. An example of the loops is shown below
# initializing matrix object where to store the dyads as [actor1,actor2,type]
dyad_mat <- matrix(NA, nrow = N*(N-1)*C, ncol = 3)
colnames(dyad_mat) <- c("actor1","actor2","type")
rownames(dyad_mat) <- 1:(N*(N-1)*C)

# initializing position index
d <- 1 

# start three loops
for(type in sorted_types){ # loop over event types, 
  for(actor1 in sorted_actors){ # loop over actor1
    for(actor2 in sorted_actors){ # loop over actor2
      if(actor1!=actor2){ # avoid self-loops
        dyad_mat[d,] <- c(actor1,actor2,type)
        d <- d + 1
      }
    }
  }
}

 # same result as showed above by using the method `getDyad()`
dyad_mat[1:5,]

# checking the size of the _full_ risk set that is 20
dim(dyad_mat)[1] 

The matrix dyad_mat above describes the full risk set and the row indices correspond to the ID of each dyad (dyadID). For instance, the dyadID is useful in the case of tie-oriented modeling, where the remify object will contain the attribute named "dyad", which describes the time-ordered sequence of ID's as to the observed dyads.

# accessing the first values of the attribute "dyad" 
# (attribute available only for tie-oriented modeling)
head(attr(reh,"dyad"))

Visualizing the risk set

A possible way for visualizing the risk set composition at each time point consists in plotting a grid with actors' names on both axes: referring to the senders (on the y-axis) and to the receivers (on the x-axis).

risk_set <- expand.grid(sorted_actors,sorted_actors)
dyad_occurred <- c(11,4,11,11)

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

# ... creating layout
layout_matrix <- matrix(c(1,2,3,4), ncol=2, byrow=TRUE) # 0 can become 4 for a legend of the colors
layout(layout_matrix, widths=c(1/2,1/2), heights=c(1/2,1/2))
# ... starting plotting
par(oma=c(2,0,2,0))
par(mar=c(6,6,1,0))
par(mgp=c(6,1,0))
par(mfrow=c(2,2))
for(m in 1:4){
value <- rep(NA,dim(risk_set)[1])
for(d in 1:length(value)){
    if(risk_set[d,1]!=risk_set[d,2]){
        if(d == dyad_occurred[m]){
            value[d] <- "#2ffd20"
        }
        else{
            value[d] <- "#b2b2b2"
        }
    }
    else{
       value[d] <- "#ffffff"
    }
}
dat <- data.frame(row=as.numeric(risk_set[,1]),col=as.numeric(risk_set[,2]),value=value)
# tile plot
plot.new()
plot.window(xlim=c(0.5,N+0.5),ylim=c(0.5,N+0.5),asp=1)
with(dat,{
rect(col-0.5,row-0.5,col+0.5,row+0.5,col=value,border="#f1f1f1")  
#segments(x0=c(1:N)+0.5,y0=c(1:N)-0.5,x1=c(1:N)-0.5,y1=c(1:N)+0.5,col="#eae8e8")
#segments(x0=0.5,y0=0.5,x1=(N+0.5),y1=(N+0.5),col="#eae8e8")
# actor names
text(x = c(1:N), y = 0, labels = sorted_actors, srt = 90, pos = 1, xpd = TRUE,  adj = c(0.5,0), offset = 1.5,cex = 0.8) 
text(x = 0, y = c(1:N), labels = sorted_actors, srt = 0, pos = 2, xpd = TRUE,  adj = c(1,0.5), offset = -0.5, cex = 0.8)
# axes names 
mtext(text  = "actor2", side=1, line=4, outer=FALSE, adj=0, at=floor(N/2),cex = 0.6)
mtext(text = "actor1", side=2, line=0, outer=FALSE, adj=1, at=floor(N/2)+1,cex = 0.6)
mtext(text = bquote(t[.(m)]), side=3, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
})
}

par(op)

Cosidering the first four time points of randomREHsmall, we observe: the (directed) dyad (Colton,Kayla) at time $t_1$, $t_3$ and $t_4$ and the (directed) dyad (Lexy,Colton) at time $t_2$. The cell corresponding to the relational event occurred at each time point is colored in green. The rest of the cells are colored in gray, indicating those dyadic events that could have occurred and they are part of the risk set. Cells in white, indicate those events that could not occur (in this case the self-loops, like (Colton,Colton), where sender and receiver are the same actor).

A full risk set in undirected networks will assume a particular grid visualization. The dyads at risk will be on the lower triangular grid, because the actor names c(actor1,actor2) describing the dyad in the input edgelist are sorted according to their alphanumeric order before being processed. For instance, the event at $t_2$ c("Lexy","Colton"), will be rearranged as c("Colton","Lexy"), and the risk set will change as follows in the picture below.

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

dyad_occurred <- c(NA,NA,16) 
for(m in 3){
value <- rep(NA,dim(risk_set)[1])
for(d in 1:dim(risk_set)[1]){
    if(risk_set[d,1]!=risk_set[d,2]){
        if(d == dyad_occurred[m]){
            value[d] <- "#2ffd20"
        }
        else if(as.character(risk_set[d,1])<as.character(risk_set[d,2])){
            value[d] <- "#b2b2b2"
        }
        else{
            value[d] <- "#ffffff"
        }
    }
}
dat <- data.frame(row=as.numeric(risk_set[,1]),col=as.numeric(risk_set[,2]),value=value)
# tile plot
plot.new()
plot.window(xlim=c(0.5,N+0.5),ylim=c(0.5,N+0.5),asp=1)
with(dat,{
rect(col-0.5,row-0.5,col+0.5,row+0.5,col=value,border="#f1f1f1")  
#segments(x0 = c(rep(seq(1.5,4.5,by=1),each=2),5.5), y0 = c(0.5,rep(seq(1.5,4.5,by=1),each=2)) , x1 = c(rep(0.5,5),seq(1.5,4.5,by=1)) , y1 =c(seq(1.5,5.5,by=1),rep(5.5,4)),col="#eae8e8")
#segments(x0 = rep(0.5,5), y0 = seq(0.5,4.5,by=1), x1 = seq(5.5,1.5,by=-1), y1 = rep(5.5,5), col="#eae8e8")

# actor names
text(x = c(1:N), y = 0, labels = sorted_actors, srt = 90, pos = 1, xpd = TRUE,  adj = c(0.5,0), offset = 1.5,cex = 0.8) 
text(x = 0, y = c(1:N), labels = sorted_actors, srt = 0, pos = 2, xpd = TRUE,  adj = c(1,0.5), offset = -0.5, cex = 0.8)
# axes names 
mtext(text  = "actor2", side=1, line=4, outer=FALSE, adj=0, at=floor(N/2))
mtext(text = "actor1", side=2, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
mtext(text = bquote(t[.(m)]), side=3, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
})
}

par(op)


The active and manual risk set

A full risk set is assumed to have a constant structure throughout the whole event history. All the possible dyads are assumed to be always at risk regardless any consideration about: (i) the possibility of one or more actors to still be able to interact with the other actors during the observation period, (ii) the possiblity of some event types to actually occur.

From this observation, the concept of a risk set structure that changes over time may accomodate certain relational event histories in which, actors, dyads or event types may not be observed within prespecified time windows. Two alternative definitions of the risk set can be declared with remify::remify():


The active risk set

There exist relational event networks that have a large number of actors and the number of observed dyads is by far lower than the potential number of dyads (i.e. the size $D$ of the full risk set).

A measure of global density can be calculated over the whole event sequence as the ratio $D_{\text{obs}}/D$, where $D_{\text{obs}}$ is the number of observed dyadic events and it can vary between $1$ and $D$. When a very low portion of dyads takes action in the network, we can think of restricting the risk set only to such observed dyads. This risk set reduction leads to the active risk set, which mantains the same structure over time but is restricted to the dyads that were observed at least one time in the event history. This type of risk set can be declared by specifying riskset = "active" in remify::remify()

The use of the active risk set can significantly decrease the computational time of both the calculation of statistics and the estimation of model parameters. However, the reduction of the risk set to the set of active (observed) dyads causes the exclusion of dyadic events that perhaps should be still included in the risk set. It is always good practice to explore the set of active dyads and take the due considerations given the type of data at hand, for instance: (i) expecting potential biases coming from the definition of an active risk set, (ii) considering to define a modification of the active risk set that avoids the exclusion of a set of additional actors/dyads/event types from the risk set even if they were not observed in the event history.


The manual risk set

There are circumstances in which one or more actors cannot take part in a relational event or an event type cannot be observed. This can happen either for a time window that can assume one of the following definitions:

To give a grasp of a few possible real scenarios in which actors/dyads/event types may be excluded from the risk set, we introduce three examples:

In such scenarios and in many others, a full risk set would account for relational events that are not feasible and this may even lead to biased estimates of the model parameters. On contrary, it is possible to account for changes of the risk set over time by defining a manual risk set.

A manual risk set consists of a time-based definition of the ensemble of dyads at risk where the user specifies which dyads to remove from the full risk set at a specific time interval of the study. This can be done via the omit_dyad argument of the function remify::remify(). The user can define multiple modifications of the full risk set occurring at different, or even overlapping, time windows. In each modification, the user specifies the set of actors, or dyads, or event types to be omitted.

Consider the first four time points of the small random network and assume this time that actors "Richard" and "Francesca" didn't join the study until the second day of the study. This means that the risk set for at least the first four time points will have the following composition,

dyad_occurred <- c(11,4,11,11) 

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

# ... creating layout
layout_matrix <- matrix(c(1,2,3,4), ncol=2, byrow=TRUE) # 0 can become 4 for a legend of the colors
layout(layout_matrix, widths=c(1/2,1/2), heights=c(1/2,1/2))
# ... starting plotting
par(oma=c(2,0,2,0))
par(mar=c(6,6,1,0))
par(mgp=c(6,1,0))
par(mfrow=c(2,2))
for(m in 1:4){
value <- rep(NA,dim(risk_set)[1])
for(d in 1:length(value)){
    if(risk_set[d,1]!=risk_set[d,2]){
        if(d == dyad_occurred[m]){
            value[d] <- "#2ffd20"
        }
        else{
            value[d] <- "#b2b2b2"
        }
        if(risk_set[d,1] %in% c("Richard","Francesca") | risk_set[d,2] %in% c("Richard","Francesca")){
          value[d] <- "#ffffff"
        }
    }
    else{
       value[d] <- "#ffffff"
    }
}
dat <- data.frame(row=as.numeric(risk_set[,1]),col=as.numeric(risk_set[,2]),value=value)
# tile plot
plot.new()
plot.window(xlim=c(0.5,N+0.5),ylim=c(0.5,N+0.5),asp=1)
with(dat,{
rect(col-0.5,row-0.5,col+0.5,row+0.5,col=value,border="#f1f1f1")  

#segments(x0=c(1:N)+0.5,y0=c(1:N)-0.5,x1=c(1:N)-0.5,y1=c(1:N)+0.5,col="#eae8e8")
#segments(x0=0.5,y0=0.5,x1=(N+0.5),y1=(N+0.5),col="#eae8e8")

# actor names
text(x = c(1:N), y = 0, labels = sorted_actors, srt = 90, pos = 1, xpd = TRUE,  adj = c(0.5,0), offset = 1.5,cex = 0.8) 
text(x = 0, y = c(1:N), labels = sorted_actors, srt = 0, pos = 2, xpd = TRUE,  adj = c(1,0.5), offset = -0.5, cex = 0.8)
# axes names 
mtext(text  = "actor2", side=1, line=4, outer=FALSE, adj=0, at=floor(N/2),cex = 0.6)
mtext(text = "actor1", side=2, line=0, outer=FALSE, adj=1, at=floor(N/2)+1,cex = 0.6)
mtext(text = bquote(t[.(m)]), side=3, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
})
}

par(op)

where the tiles defining the dyads where "Richard" and "Francesca" are either the sender (actor1) or receiver (actor2) are excluded from the risk set (the tiles are now in white). The risk set is now made of only those dyads in which "Colton", "Kayla" and "Lexy"are either the sender or the receiver of a relational event (tiles in gray).

Finally, a manual risk set can be defined also for undirected networks and the grid visualization will focus on the lower triangular grid, because the actor names c(actor1,actor2) describing the dyad in the input edgelist are sorted according to their alphanumeric order by the processing. For instance, the event at $t_2$ c("Lexy","Colton"), will be rearranged as c("Colton","Lexy"), thus the risk set will change as below.

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

dyad_occurred <- c(NA,NA,16) 
for(m in 3){
value <- rep(NA,dim(risk_set)[1])
for(d in 1:length(value)){
    if(risk_set[d,1]!=risk_set[d,2]){
        if(d == dyad_occurred[m]){
            value[d] <- "#2ffd20"
        }
        else if(as.character(risk_set[d,1])<as.character(risk_set[d,2])){
            value[d] <- "#b2b2b2"
        }
        if(risk_set[d,1] %in% c("Richard","Francesca") | risk_set[d,2] %in% c("Richard","Francesca")){
          value[d] <- "#ffffff"
        }
    }
    else{
       value[d] <- "#ffffff"
    }
}
dat <- data.frame(row=as.numeric(risk_set[,1]),col=as.numeric(risk_set[,2]),value=value)
# tile plot
plot.new()
plot.window(xlim=c(0.5,N+0.5),ylim=c(0.5,N+0.5),asp=1)
with(dat,{
rect(col-0.5,row-0.5,col+0.5,row+0.5,col=value,border="#f1f1f1")  
# actor names
text(x = c(1:N), y = 0, labels = sorted_actors, srt = 90, pos = 1, xpd = TRUE,  adj = c(0.5,0), offset = 1.5,cex = 0.8) 
text(x = 0, y = c(1:N), labels = sorted_actors, srt = 0, pos = 2, xpd = TRUE,  adj = c(1,0.5), offset = -0.5, cex = 0.8)
# axes names 
mtext(text  = "actor2", side=1, line=4, outer=FALSE, adj=0, at=floor(N/2))
mtext(text = "actor1", side=2, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
mtext(text = bquote(t[.(m)]), side=3, line=0, outer=FALSE, adj=1, at=floor(N/2)+1)
})
}

par(op)

Specifying a manual risk set: the omit_dyad argument

The input argument omit_dyad is required when the argument riskset = "manual". With this argument, the user describes the time windows and the actor/dyads/event types to exclude from them. The object to supply via the argumen omit_dyad consists of a list of modifications. Each list refers to one risk set modification and must be a list of two objects: a data.frame called dyad, where dyads to be removed are specified by row in the format actor1, actor2, type, and a vector called time which describes the first and last time point of the time window where to apply the modification.

Example on five risk set modifications

Consider the randomREH data.

data(randomREH)

For instance, we want to modify (reduce) the risk set according to five changes that apply on different time intervals:

  1. an event type conflict that was no more feasible since a specific time point until the end of the observation period.
randomREH$omit_dyad[[1]]$time # start and stop time point defining the time window of interest
randomREH$omit_dyad[[1]]$dyad # dyads to be removed from the time points defined by the interval in `time`
  1. two actors Michaela and Zackary that couldn't interact with anybody else after a specific time point until the last observed time point.
randomREH$omit_dyad[[2]]$time
randomREH$omit_dyad[[2]]$dyad

The object dyad will give instructions such that the function will remove from the risk set at the indicated time windows all the events where: (1) type is conflict, (2) Michaela and `Zackary are senders or receivers.

In this example we also add three more modifications of the risk set that are not present in the object randomREH$omit_dyad but that allow to explain how the input omit_dyad works, and also how the processed risk set object will look like (in the next section):

  1. actors Maya, Alexander, Richard and Charles joined the network after the start of the event history.
randomREH$omit_dyad[[3]] <- list()
randomREH$omit_dyad[[3]]$time <- c(randomREH$edgelist$time[3500],randomREH$edgelist$time[3500])
randomREH$omit_dyad[[3]]$time[1] <- NA
randomREH$omit_dyad[[3]]$dyad <- data.frame(actor1=c("Maya","Alexander","Richard","Charles",rep(NA,4)),actor2= c(rep(NA,4),"Maya","Alexander","Richard","Charles"),type=rep(NA,8))
randomREH$omit_dyad[[3]]$time 
randomREH$omit_dyad[[3]]$dyad 
  1. actor Breanna left the network during a long time interval (about 2 months) embedded in the event history.
randomREH$omit_dyad[[4]] <- list()
randomREH$omit_dyad[[4]]$time <- c(randomREH$edgelist$time[2800],randomREH$edgelist$time[8700])
randomREH$omit_dyad[[4]]$dyad <- data.frame(actor1=c("Breanna",NA),actor2= c(NA,"Breanna"),type=rep(NA,2))
randomREH$omit_dyad[[4]]$time
randomREH$omit_dyad[[4]]$dyad
  1. actor Megan left the network for a few days.
randomREH$omit_dyad[[5]] <- list()
randomREH$omit_dyad[[5]]$time <- c(randomREH$edgelist$time[7000],randomREH$edgelist$time[7500])
randomREH$omit_dyad[[5]]$dyad <- data.frame(actor1=c("Megan",NA),actor2= c(NA,"Megan"),type=rep(NA,2))
randomREH$omit_dyad[[5]]$time
randomREH$omit_dyad[[5]]$dyad

Using NA values to remove sets of actors/dyads/event types

The <NA> values mean that all the actors/event types are considered in that field. Indeed, in the change 1. where we needed to remove all the events where conflict was the type, we did it by leaving both actor1 and actor2 unspecified <NA>. Therefore, every time one of the fields among (actor1,actor2,type) is left undefined, the reduction applies to all the possible values of that field. Another example are the risk set chages declared in 4. and 5., where we wanted to exclude all the dyads in which Breanna and Megan are either the sender or the receiver of a relational event. Therefore, we defined a data.frame named "dyad" with two rows: one row in which Breanna(Megan) appeared as the sender, and a second row in which Breanna (Megan) appeared as the receiver. We left the other fields set to NA, meaning that (by row) all the possible event types and actors are to be considered.

Visualizing the risk set modifications declared with omit_dyad (before the processing)

We can visualize the risk set modifications as they are declared via the omit_dyad argument in a plot where the x-axis represents the time and the y-axis describes the five risk set modifications presented above.

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

min_max_omit_dyad <-range(randomREH$edgelist$time)
plot(min_max_omit_dyad,c(0,length(randomREH$omit_dyad)+1),type="n",yaxt="n",xlab="time",ylab="modification",main="manual risk set \n (input modifications declared with the omit_dyad argument)")
axis(2, at=c(1:length(randomREH$omit_dyad)))
for(r in 1:length(randomREH$omit_dyad)){
    if(is.na(randomREH$omit_dyad[[r]]$time[1])){ # if start time is not specified
        randomREH$omit_dyad[[r]]$time <- c(randomREH$edgelist$time[1],randomREH$omit_dyad[[r]]$time[2])
    }
    if(is.na(randomREH$omit_dyad[[r]]$time[2])){ # if stop time is not specified
        randomREH$omit_dyad[[r]]$time <- c(randomREH$omit_dyad[[r]]$time[1],randomREH$edgelist$time[dim(randomREH$edgelist)[1]])
    }
    segments(x0=randomREH$omit_dyad[[r]]$time[1],y0=r,x1=randomREH$omit_dyad[[r]]$time[2],y1=r,col="black", lwd = 2)
    #randomREH$omit_dyad[[r]]$time
}

par(op)

The processed risk set

The function remify::remify() processes the list of modifications supplied to omit_dyad (only when riskset = "manual"). The aim is to elaborate the risk set modifications by accounting for the possible partial/complete overlapping of time windows. A way to understand whatthe processing does is to consider the plot of the input modifications and show the plot of the final processing.

edgelist_reh <- remify::remify(edgelist = randomREH$edgelist,
                    directed = TRUE, # events are directed
                    ordinal = FALSE, # model with waiting times
                    model = "tie", # tie-oriented modeling
                    actors = randomREH$actors,
                    types = randomREH$types, 
                    riskset = "manual",
                    origin = randomREH$origin,
                    omit_dyad = randomREH$omit_dyad)

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

min_max_omit_dyad <-range(randomREH$edgelist$time)
plot(min_max_omit_dyad,c(0,length(randomREH$omit_dyad)+1),type="n",yaxt="n",xlab="time",ylab="modification",main="manual risk set \n (before processing)")
axis(2, at=c(1:length(randomREH$omit_dyad)))
for(r in 1:length(randomREH$omit_dyad)){
    if(is.na(randomREH$omit_dyad[[r]]$time[1])){ # if start time is not specified
        randomREH$omit_dyad[[r]]$time <- c(randomREH$edgelist$time[1],randomREH$omit_dyad[[r]]$time[2])
    }
    if(is.na(randomREH$omit_dyad[[r]]$time[2])){ # if stop time is not specified
        randomREH$omit_dyad[[r]]$time <- c(randomREH$omit_dyad[[r]]$time[1],randomREH$edgelist$time[dim(randomREH$edgelist)[1]])
    }
    segments(x0=randomREH$omit_dyad[[r]]$time[1],y0=r,x1=randomREH$omit_dyad[[r]]$time[2],y1=r,col="black", lwd = 2)
    #randomREH$omit_dyad[[r]]$time
}

par(op)

The processing function understands the partial/complete overlapping of the time windows and defines new time intervals in which one or more risk set changes are observed. In the plot below, the vertical boundaries (dashed red lines) indicate the time intervals. Such time bounds are used from the processing function to intersect the time windows decalred in omit_dyad and define new time intervals, where the changes of the risk set are processed according to the new time windows. If the user supplies time windows that are not overlapping, then the processed risk set will have the same structure of the input.

# processing here the output for the plot below 
modification_idx <- sort(unique(edgelist_reh$omit_dyad$time))
start_stop_times <- data.frame(start = rep(randomREH$edgelist$time[1],length(modification_idx)),
                               stop = rep(randomREH$edgelist$time[1],length(modification_idx)))
for(i in 1:length(modification_idx)){
 start_stop_idx <- range(which(edgelist_reh$omit_dyad$time == modification_idx[i]))
 start_stop_times[i,1] <- randomREH$edgelist$time[start_stop_idx[1]]
 start_stop_times[i,2] <- randomREH$edgelist$time[start_stop_idx[2]]
}

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

# plotting vertical lines and different colour for the intersected intervals
plot(min_max_omit_dyad,c(0,length(randomREH$omit_dyad)+1),type="n",yaxt="n",xlab="time",ylab="modification",main="manual risk set \n (while processing)")
axis(2, at=c(1:length(randomREH$omit_dyad)))
for(r in 1:length(randomREH$omit_dyad)){
    segments(x0=randomREH$omit_dyad[[r]]$time[1],y0=r,x1=randomREH$omit_dyad[[r]]$time[2],y1=r,col="black", lwd = 2)
}
abline(v = unique(c(start_stop_times$start, start_stop_times$stop)) , lwd = 1, lty = 2, col = "red")

par(op)

After the processing of a relational event history, the remify object will contain a list called omit_dyad where two objects (time and riskset) will describe the processed risk set modifications. As a result of the processing of the five risk set modifications, the risk set is describe now by eight risk set modifications. This is due to the partial/total overlapping of two or more time intervals. For instance, the second modification of the processed risk set (figure below) will contain the combination of the third and the fourth modification declared in the input omit_dyad (figure above).

# ... saving current graphical parameters
op <- par(no.readonly = TRUE)

plot(min_max_omit_dyad,c(0,length(modification_idx)+1),type="n",yaxt="n",xlab="time",ylab="modification",main="manual risk set \n (after processing)")
axis(2, at=c(1:length(modification_idx)))
for(r in 1:length(modification_idx)){
    segments(x0=start_stop_times[r,1],y0=r,x1=start_stop_times[r,2],y1=r, lwd = 2,col="black")
    #randomREH$omit_dyad[[r]]$time
}

par(op)



Try the remify package in your browser

Any scripts or data that you put into this service are public.

remify documentation built on Nov. 22, 2023, 5:07 p.m.