sampling.robustness {ANTs}  R Documentation 
Performs a matrix boostrapping approach to estimate the confidence intervals surrounding each pairwise association.
sampling.robustness(
df,
subsampling = c(5, 10, 20, 30, 40, 50),
metric = "met.strength",
assoc.indices = FALSE,
actor,
receiver,
scan,
id,
index = "sri",
progress = TRUE,
...
)
df 
a data frame of individual associations 
subsampling 
a vector of integers indicating the percentage of data to remove 
metric 
the network metric to compute 
assoc.indices 
a bolean indicating if association indices must be used 
actor 
If argument assoc.indices is FALSE, fill this argument, an integer or a string indicating the column of the individuals performing the behaviour. 
receiver 
If argument assoc.indices is FALSE, fill this argument, an integer or a string indicating the column of the individuals receiving the behaviour. 
scan 
If argument assoc.indices is TRUE, fill this argument, a numeric or character vector representing one or more columns used as scan factors. 
id 
If argument assoc.indices is TRUE, fill this argument, a numeric or character vector indicating the column holding ids of individuals. 
index 
a string indicating the association index to compute: 
progress 
a boolean indicating if function should print progress. 
... 
additional argument related to the computation of the metric declared.

This process evaluates network metrics robustness by performing a bootstrap process to remove a certain percent of the data collected and recomputing the network metric of interest. This has been used in Balasubramaniam et al. 2018 to assess sensitivty of sampling effort of global network metrics in primate networks.
3 elements:
A matrix in which each columns represent a node metric variation throough bootstraping, with the first row representing the original metric.
A summary of bootstrap distribution for each nodes.
A plot of metric variations through deletions
Sebastian Sosa
Balasubramaniam, K. N., Beisner, B. A., Berman, C. M., De Marco, A., Duboscq, J., Koirala, S., ... & Ogawa, H. (2018). The influence of phylogeny, social style, and sociodemographic factors on macaque social network structure. American journal of primatology, 80(1), e22727.
#Example for node measures
test < sampling.robustness(sim.focal.directed, actor = "actor",
receiver = "receiver", metric = "met.strength")
# objects returned by the function
test$metrics
test$summary
test$plot
# Examples with metric extra arguments
sampling.robustness(sim.focal.directed, actor = "actor",
receiver = "receiver", metric = "met.affinity")
sampling.robustness(sim.focal.directed, actor = "actor",
receiver = "receiver", metric = "met.affinity", binary = FALSE)
# Examples with association data
test2 < sampling.robustness(df = sim.grp, assoc.indices = TRUE,
scan = c("time", "location"), id = "ID", metric = "met.strength")
# Example of how to test global network metric robustness
#by removing 10% of the observations simulated 100 times
test < sampling.robustness(sim.focal.directed, subsampling = rep(10, 100),
actor = "actor", receiver = "receiver", metric = "met.diameter")