A Stein goodness-of-test for exponential random graph models
We propose and analyse a novel nonparametric goodness-of-fit testing procedure for exchangeable exponential random graph model (ERGM) when a single network realisation is observed. The test determines how likely it is that the observation is generated from a target unnormalised ERGM density. Our tes...
| Main Authors: | , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Journal of Machine Learning Research
2021
|
| _version_ | 1826294165996044288 |
|---|---|
| author | Xu, W Reinert, G |
| author_facet | Xu, W Reinert, G |
| author_sort | Xu, W |
| collection | OXFORD |
| description | We propose and analyse a novel nonparametric goodness-of-fit testing procedure for exchangeable exponential random graph model (ERGM) when a single network realisation is observed. The test determines how likely it is that the observation is generated from a target unnormalised ERGM density. Our test statistics are derived of kernel Stein discrepancy, a divergence constructed via Stein’s method using functions from a reproducing kernel Hilbert space (RKHS), combined with a discrete Stein operator for ERGMs. The test is a Monte Carlo test using simulated networks from the target ERGM. We show theoretical properties for the testing procedure w.r.t a class of ERGMs. Simulation studies and real network applications are presented. |
| first_indexed | 2024-03-07T03:41:26Z |
| format | Journal article |
| id | oxford-uuid:be067c94-0f3e-449d-9b57-f438211bba47 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T03:41:26Z |
| publishDate | 2021 |
| publisher | Journal of Machine Learning Research |
| record_format | dspace |
| spelling | oxford-uuid:be067c94-0f3e-449d-9b57-f438211bba472022-03-27T05:36:15ZA Stein goodness-of-test for exponential random graph modelsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:be067c94-0f3e-449d-9b57-f438211bba47EnglishSymplectic ElementsJournal of Machine Learning Research2021Xu, WReinert, GWe propose and analyse a novel nonparametric goodness-of-fit testing procedure for exchangeable exponential random graph model (ERGM) when a single network realisation is observed. The test determines how likely it is that the observation is generated from a target unnormalised ERGM density. Our test statistics are derived of kernel Stein discrepancy, a divergence constructed via Stein’s method using functions from a reproducing kernel Hilbert space (RKHS), combined with a discrete Stein operator for ERGMs. The test is a Monte Carlo test using simulated networks from the target ERGM. We show theoretical properties for the testing procedure w.r.t a class of ERGMs. Simulation studies and real network applications are presented. |
| spellingShingle | Xu, W Reinert, G A Stein goodness-of-test for exponential random graph models |
| title | A Stein goodness-of-test for exponential random graph models |
| title_full | A Stein goodness-of-test for exponential random graph models |
| title_fullStr | A Stein goodness-of-test for exponential random graph models |
| title_full_unstemmed | A Stein goodness-of-test for exponential random graph models |
| title_short | A Stein goodness-of-test for exponential random graph models |
| title_sort | stein goodness of test for exponential random graph models |
| work_keys_str_mv | AT xuw asteingoodnessoftestforexponentialrandomgraphmodels AT reinertg asteingoodnessoftestforexponentialrandomgraphmodels AT xuw steingoodnessoftestforexponentialrandomgraphmodels AT reinertg steingoodnessoftestforexponentialrandomgraphmodels |