FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104810320> ?p ?o ?g. }

• W3104810320 endingPage "1777" @default.
• W3104810320 startingPage "1765" @default.
• W3104810320 abstract "Semiparametric regression offers a flexible framework for modeling nonlinear relationships between a response and covariates. A prime example are generalized additive models (GAMs) where splines (say) are used to approximate nonlinear functional components in conjunction with a quadratic penalty to control for overfitting. Estimation and inference are then generally performed based on the penalized likelihood, or under a mixed model framework. The penalized likelihood framework is fast but potentially unstable, and choosing the smoothing parameters needs to be done externally using cross-validation, for instance. The mixed model framework tends to be more stable and offers a natural way for choosing the smoothing parameters, but for nonnormal responses involves an intractable integral. In this article, we introduce a new framework for semiparametric regression based on variational approximations (VA). The approach possesses the stability and natural inference tools of the mixed model framework, while achieving computation times comparable to using penalized likelihood. Focusing on GAMs, we derive fully tractable variational likelihoods for some common response types. We present several features of the VA framework for inference, including a variational information matrix for inference on parametric components, and a closed-form update for estimating the smoothing parameter. We demonstrate the consistency of the VA estimates, and an asymptotic normality result for the parametric component of the model. Simulation studies show the VA framework performs similarly to and sometimes better than currently available software for fitting GAMs. Supplementary materials for this article are available online." @default.
• W3104810320 created "2020-11-23" @default.
• W3104810320 creator A5000251612 @default.
• W3104810320 creator A5009817898 @default.
• W3104810320 creator A5064317084 @default.
• W3104810320 creator A5087947210 @default.
• W3104810320 date "2019-02-27" @default.
• W3104810320 modified "2023-10-18" @default.
• W3104810320 title "Semiparametric Regression Using Variational Approximations" @default.
• W3104810320 cites W1423766661 @default.
• W3104810320 cites W1969640518 @default.
• W3104810320 cites W1988300874 @default.
• W3104810320 cites W1990420052 @default.
• W3104810320 cites W2008573898 @default.
• W3104810320 cites W2014360396 @default.
• W3104810320 cites W2014581807 @default.
• W3104810320 cites W2024378992 @default.
• W3104810320 cites W2025720061 @default.
• W3104810320 cites W2027106381 @default.
• W3104810320 cites W2027235406 @default.
• W3104810320 cites W2049633694 @default.
• W3104810320 cites W2052309176 @default.
• W3104810320 cites W2059424427 @default.
• W3104810320 cites W2078703947 @default.
• W3104810320 cites W2078810282 @default.
• W3104810320 cites W2093083068 @default.
• W3104810320 cites W2119160928 @default.
• W3104810320 cites W2119753634 @default.
• W3104810320 cites W2133944729 @default.
• W3104810320 cites W2140641091 @default.
• W3104810320 cites W2154065358 @default.
• W3104810320 cites W2166163519 @default.
• W3104810320 cites W2307276676 @default.
• W3104810320 cites W2567289819 @default.
• W3104810320 cites W2964195345 @default.
• W3104810320 cites W3099640513 @default.
• W3104810320 cites W3101380508 @default.
• W3104810320 cites W3122992882 @default.
• W3104810320 cites W4298870098 @default.
• W3104810320 doi "https://doi.org/10.1080/01621459.2018.1518235" @default.
• W3104810320 hasPublicationYear "2019" @default.
• W3104810320 type Work @default.
• W3104810320 sameAs 3104810320 @default.
• W3104810320 citedByCount "7" @default.
• W3104810320 countsByYear W31048103202021 @default.
• W3104810320 countsByYear W31048103202022 @default.
• W3104810320 countsByYear W31048103202023 @default.
• W3104810320 crossrefType "journal-article" @default.
• W3104810320 hasAuthorship W3104810320A5000251612 @default.
• W3104810320 hasAuthorship W3104810320A5009817898 @default.
• W3104810320 hasAuthorship W3104810320A5064317084 @default.
• W3104810320 hasAuthorship W3104810320A5087947210 @default.
• W3104810320 hasBestOaLocation W31048103202 @default.
• W3104810320 hasConcept C105795698 @default.
• W3104810320 hasConcept C11413529 @default.
• W3104810320 hasConcept C117251300 @default.
• W3104810320 hasConcept C126255220 @default.
• W3104810320 hasConcept C129844170 @default.
• W3104810320 hasConcept C154945302 @default.
• W3104810320 hasConcept C19539793 @default.
• W3104810320 hasConcept C2524010 @default.
• W3104810320 hasConcept C2776214188 @default.
• W3104810320 hasConcept C28826006 @default.
• W3104810320 hasConcept C33923547 @default.
• W3104810320 hasConcept C3770464 @default.
• W3104810320 hasConcept C41008148 @default.
• W3104810320 hasConceptScore W3104810320C105795698 @default.
• W3104810320 hasConceptScore W3104810320C11413529 @default.
• W3104810320 hasConceptScore W3104810320C117251300 @default.
• W3104810320 hasConceptScore W3104810320C126255220 @default.
• W3104810320 hasConceptScore W3104810320C129844170 @default.
• W3104810320 hasConceptScore W3104810320C154945302 @default.
• W3104810320 hasConceptScore W3104810320C19539793 @default.
• W3104810320 hasConceptScore W3104810320C2524010 @default.
• W3104810320 hasConceptScore W3104810320C2776214188 @default.
• W3104810320 hasConceptScore W3104810320C28826006 @default.
• W3104810320 hasConceptScore W3104810320C33923547 @default.
• W3104810320 hasConceptScore W3104810320C3770464 @default.
• W3104810320 hasConceptScore W3104810320C41008148 @default.
• W3104810320 hasIssue "528" @default.
• W3104810320 hasLocation W31048103201 @default.
• W3104810320 hasLocation W31048103202 @default.
• W3104810320 hasLocation W31048103203 @default.
• W3104810320 hasLocation W31048103204 @default.
• W3104810320 hasOpenAccess W3104810320 @default.
• W3104810320 hasPrimaryLocation W31048103201 @default.
• W3104810320 hasRelatedWork W1676787740 @default.
• W3104810320 hasRelatedWork W1970987673 @default.
• W3104810320 hasRelatedWork W2004492308 @default.
• W3104810320 hasRelatedWork W2386767533 @default.
• W3104810320 hasRelatedWork W2388501007 @default.
• W3104810320 hasRelatedWork W2590671464 @default.
• W3104810320 hasRelatedWork W3021793061 @default.
• W3104810320 hasRelatedWork W3135313048 @default.
• W3104810320 hasRelatedWork W4225891298 @default.
• W3104810320 hasRelatedWork W4385485567 @default.
• W3104810320 hasVolume "114" @default.
• W3104810320 isParatext "false" @default.

• next