Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Байєсівський аналіз мереж еґо× | Байєсівська експоненційна випадкова графова модель× | |
|---|---|---|
| Галузь | Мережевий аналіз | Мережевий аналіз |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2010s | 2011 |
| Автор методу≠ | Various (Bayesian SNA tradition; Krivitsky, Kolaczyk, Handcock among key contributors) | Caimo, A., & Friel, N. |
| Тип≠ | Probabilistic network model | Bayesian statistical model for networks |
| Основоположне джерело≠ | Krivitsky, P. N., & Kolaczyk, E. D. (2015). On the question of effective sample size in network modeling: An asymptotic inquiry. Statistical Science, 30(2), 184–198. DOI ↗ | Caimo, A., & Friel, N. (2011). Bayesian inference for exponential random graph models. Social Networks, 33(1), 41–55. DOI ↗ |
| Інші назви | Bayesian personal network analysis, Bayesian egocentric network analysis, probabilistic ego network modeling, Bayesian egonet | Bayesian ERGM, Bayesian p-star model, Bayesian p* model, BERGM |
| Пов'язані≠ | 5 | 4 |
| Підсумок≠ | Bayesian ego network analysis applies probabilistic inference to ego-centered (personal) network data, combining a likelihood model for the ego's local network with prior distributions over network parameters. The result is a full posterior distribution that quantifies uncertainty about structural features such as alter composition, tie density, and network size — rather than producing point estimates alone. | The Bayesian Exponential Random Graph Model (Bayesian ERGM or BERGM) extends the classical ERGM framework by placing prior distributions over the model parameters and using Markov chain Monte Carlo methods to obtain full posterior distributions. Introduced by Caimo and Friel (2011), it allows researchers to quantify parameter uncertainty and incorporate prior knowledge when modelling the structural features of social and other complex networks. |
| ScholarGateНабір даних ↗ |
|
|