Estimation and prediction for stochastic blockstructures
A statistical approach to a posteriori blockmodeling for digraphs and valued digraphs is proposed. The probability model assumes that the vertices of the digraph are partitioned into several unobserved (latent) classes and that the probability distribution of the relation between two vertices depend...
| Autors principals: | , |
|---|---|
| Format: | Journal article |
| Idioma: | English |
| Publicat: |
2001
|
| _version_ | 1826271819451072512 |
|---|---|
| author | Nowicki, K Snijders, T |
| author_facet | Nowicki, K Snijders, T |
| author_sort | Nowicki, K |
| collection | OXFORD |
| description | A statistical approach to a posteriori blockmodeling for digraphs and valued digraphs is proposed. The probability model assumes that the vertices of the digraph are partitioned into several unobserved (latent) classes and that the probability distribution of the relation between two vertices depends only on the classes to which they belong. A Bayesian estimator based on Gibbs sampling is proposed. The basic model is not identified, because class labels are arbitrary. The resulting identifiability problems are solved by restricting inference to the posterior distributions of invariant functions of the parameters and the vertex class membership. In addition, models are considered where class labels are identified by prior distributions for the class membership of some of the vertices. The model is illustrated by an example from the social networks literature (Kapferer's tailor shop). |
| first_indexed | 2024-03-06T22:02:44Z |
| format | Journal article |
| id | oxford-uuid:4f24af2b-cde2-4836-9614-9c9e53473677 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:02:44Z |
| publishDate | 2001 |
| record_format | dspace |
| spelling | oxford-uuid:4f24af2b-cde2-4836-9614-9c9e534736772022-03-26T16:05:25ZEstimation and prediction for stochastic blockstructuresJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:4f24af2b-cde2-4836-9614-9c9e53473677EnglishSymplectic Elements at Oxford2001Nowicki, KSnijders, TA statistical approach to a posteriori blockmodeling for digraphs and valued digraphs is proposed. The probability model assumes that the vertices of the digraph are partitioned into several unobserved (latent) classes and that the probability distribution of the relation between two vertices depends only on the classes to which they belong. A Bayesian estimator based on Gibbs sampling is proposed. The basic model is not identified, because class labels are arbitrary. The resulting identifiability problems are solved by restricting inference to the posterior distributions of invariant functions of the parameters and the vertex class membership. In addition, models are considered where class labels are identified by prior distributions for the class membership of some of the vertices. The model is illustrated by an example from the social networks literature (Kapferer's tailor shop). |
| spellingShingle | Nowicki, K Snijders, T Estimation and prediction for stochastic blockstructures |
| title | Estimation and prediction for stochastic blockstructures |
| title_full | Estimation and prediction for stochastic blockstructures |
| title_fullStr | Estimation and prediction for stochastic blockstructures |
| title_full_unstemmed | Estimation and prediction for stochastic blockstructures |
| title_short | Estimation and prediction for stochastic blockstructures |
| title_sort | estimation and prediction for stochastic blockstructures |
| work_keys_str_mv | AT nowickik estimationandpredictionforstochasticblockstructures AT snijderst estimationandpredictionforstochasticblockstructures |