The missSBM package provides five functions:
simulatea function to define and draw network data according to a stochastic block model
samplea function to sample an existing network according to a variety of sampling designs
estimatea function to perform inference of SBM from network data with missing entries under various sampling designs.
prepare_dataa function to format real-world network data (adjacency matrix and covariates) to perform the estimation under missing data condition
smootha function to smooth an existing collection of SBM estimation, to avoid being trapped in local maxima.
These function leads to the manipulation of a variety of R object, with their respective fields and methods. They are all automatically generated by the top-level functions itemized above, so that the user should generally to use their constructor or internal methods directly. The user should only have a basic understanding of the fields of each object to manipulate the output in R. The main objects are the following:
sampledNetworkan object to store sampled network data (i.e. with missing dyads)
SBM_sampleran object to define a SBM to sample from
SBM_fitan object to define and store an SBM fit
networkSampleran object to define a network sampling to sample from
networkSamplingan object to define and store a network sampling fit
missSBM_fitan object that put together an SBM fit and and network sampling fit - the main point of the missSBM package !
missSBM_collectionan object to store a collection of missSBM_fit, ordered by number of block
Timoth<U+00E9>e Tabouy, Pierre Barbillon & Julien Chiquet (2019) <U+201C>Variational Inference for Stochastic Block Models from Sampled Data<U+201D>, Journal of the American Statistical Association, <doi:10.1080/01621459.2018.1562934>