Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328114192> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4328114192 abstract "The issue of model uncertainty has been gaining interest in education and the social sciences community over the years, and the dominant methods for handling model uncertainty are based on Bayesian inference, and particularly, Bayesian model averaging. However, Bayesian model averaging seeks a single best model which assumes that the true generating model is in the model space. Unlike Bayesian model averaging, the method of Bayesian stacking can account for model uncertainty without assuming that a true model exists. An issue with Bayesian stacking, however, is that it is an optimization technique that uses input-independent model weights and is, therefore, not fully Bayesian. Bayesian hierarchical stacking, proposed by Yao, Pirš, Vehtari, and Gelman (2021), further incorporates uncertainty by applying a hyperprior to the stacking weights. Considering the importance of multilevel models commonly applied in educational settings, this paper investigates the predictive performance of original Bayesian stacking and Bayesian hierarchical stacking along with two other readily available methods based on Bayesian model averaging weighting via a simulation study and a real data example from PISA 2018. Predictive performance is measured by the log predictive density and the Kullback-Leibler divergence scores. Results suggest that Bayesian hierarchical stacking performs consistently better than original Bayesian stacking and other BMA-based weighting systems in terms of predictive performance in multilevel models." @default.
- W4328114192 created "2023-03-22" @default.
- W4328114192 creator A5081723300 @default.
- W4328114192 creator A5091857976 @default.
- W4328114192 date "2023-03-21" @default.
- W4328114192 modified "2023-10-17" @default.
- W4328114192 title "Bayesian Stacking In Multilevel Models" @default.
- W4328114192 doi "https://doi.org/10.31234/osf.io/e9m6x" @default.
- W4328114192 hasPublicationYear "2023" @default.
- W4328114192 type Work @default.
- W4328114192 citedByCount "0" @default.
- W4328114192 crossrefType "posted-content" @default.
- W4328114192 hasAuthorship W4328114192A5081723300 @default.
- W4328114192 hasAuthorship W4328114192A5091857976 @default.
- W4328114192 hasBestOaLocation W43281141921 @default.
- W4328114192 hasConcept C101112237 @default.
- W4328114192 hasConcept C107673813 @default.
- W4328114192 hasConcept C119857082 @default.
- W4328114192 hasConcept C121332964 @default.
- W4328114192 hasConcept C149569020 @default.
- W4328114192 hasConcept C154945302 @default.
- W4328114192 hasConcept C160234255 @default.
- W4328114192 hasConcept C183115368 @default.
- W4328114192 hasConcept C191413810 @default.
- W4328114192 hasConcept C24890656 @default.
- W4328114192 hasConcept C33347731 @default.
- W4328114192 hasConcept C37903108 @default.
- W4328114192 hasConcept C41008148 @default.
- W4328114192 hasConcept C46141821 @default.
- W4328114192 hasConcept C71983512 @default.
- W4328114192 hasConceptScore W4328114192C101112237 @default.
- W4328114192 hasConceptScore W4328114192C107673813 @default.
- W4328114192 hasConceptScore W4328114192C119857082 @default.
- W4328114192 hasConceptScore W4328114192C121332964 @default.
- W4328114192 hasConceptScore W4328114192C149569020 @default.
- W4328114192 hasConceptScore W4328114192C154945302 @default.
- W4328114192 hasConceptScore W4328114192C160234255 @default.
- W4328114192 hasConceptScore W4328114192C183115368 @default.
- W4328114192 hasConceptScore W4328114192C191413810 @default.
- W4328114192 hasConceptScore W4328114192C24890656 @default.
- W4328114192 hasConceptScore W4328114192C33347731 @default.
- W4328114192 hasConceptScore W4328114192C37903108 @default.
- W4328114192 hasConceptScore W4328114192C41008148 @default.
- W4328114192 hasConceptScore W4328114192C46141821 @default.
- W4328114192 hasConceptScore W4328114192C71983512 @default.
- W4328114192 hasLocation W43281141921 @default.
- W4328114192 hasLocation W43281141922 @default.
- W4328114192 hasOpenAccess W4328114192 @default.
- W4328114192 hasPrimaryLocation W43281141921 @default.
- W4328114192 hasRelatedWork W2081420412 @default.
- W4328114192 hasRelatedWork W217127105 @default.
- W4328114192 hasRelatedWork W2352852554 @default.
- W4328114192 hasRelatedWork W2939130140 @default.
- W4328114192 hasRelatedWork W4235165088 @default.
- W4328114192 hasRelatedWork W4297026079 @default.
- W4328114192 hasRelatedWork W4328114192 @default.
- W4328114192 hasRelatedWork W561902361 @default.
- W4328114192 hasRelatedWork W786367546 @default.
- W4328114192 hasRelatedWork W1919985504 @default.
- W4328114192 isParatext "false" @default.
- W4328114192 isRetracted "false" @default.
- W4328114192 workType "article" @default.