FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951714489> ?p ?o ?g. }

• W2951714489 abstract "In statistical prediction, classical approaches for model selection and model evaluation based on covariance penalties are still widely used. Most of the literature on this topic is based on what we call the assumption, where covariate values are assumed to be nonrandom. By contrast, it is often more reasonable to take a view, where the covariate values are independently drawn for both training and prediction. To study the applicability of covariance penalties in this setting, we propose a decomposition of Random-X prediction error in which the randomness in the covariates contributes to both the bias and variance components. This decomposition is general, but we concentrate on the fundamental case of least squares regression. We prove that in this setting the move from Fixed-X to Random-X prediction results in an increase in both bias and variance. When the covariates are normally distributed and the linear model is unbiased, all terms in this decomposition are explicitly computable, which yields an extension of Mallows' Cp that we call $RCp$. $RCp$ also holds asymptotically for certain classes of nonnormal covariates. When the noise variance is unknown, plugging in the usual unbiased estimate leads to an approach that we call $hat{RCp}$, which is closely related to Sp (Tukey 1967), and GCV (Craven and Wahba 1978). For excess bias, we propose an estimate based on the shortcut-formula for ordinary cross-validation (OCV), resulting in an approach we call $RCp^+$. Theoretical arguments and numerical simulations suggest that $RCP^+$ is typically superior to OCV, though the difference is small. We further examine the Random-X error of other popular estimators. The surprising result we get for ridge regression is that, in the heavily-regularized regime, Random-X variance is smaller than Fixed-X variance, which can lead to smaller overall Random-X error." @default.
• W2951714489 created "2019-06-27" @default.
• W2951714489 creator A5039021124 @default.
• W2951714489 creator A5076708141 @default.
• W2951714489 date "2017-04-26" @default.
• W2951714489 modified "2023-09-27" @default.
• W2951714489 title "From Fixed-X to Random-X Regression: Bias-Variance Decompositions, Covariance Penalties, and Prediction Error Estimation" @default.
• W2951714489 cites W1484867920 @default.
• W2951714489 cites W1502338185 @default.
• W2951714489 cites W1554944419 @default.
• W2951714489 cites W1777518721 @default.
• W2951714489 cites W1990381576 @default.
• W2951714489 cites W1995691260 @default.
• W2951714489 cites W2003202757 @default.
• W2951714489 cites W2054434031 @default.
• W2951714489 cites W2054640142 @default.
• W2951714489 cites W2058815839 @default.
• W2951714489 cites W2079356438 @default.
• W2951714489 cites W2082347462 @default.
• W2951714489 cites W2089075540 @default.
• W2951714489 cites W2111814036 @default.
• W2951714489 cites W2140170995 @default.
• W2951714489 cites W2143684265 @default.
• W2951714489 cites W2146766088 @default.
• W2951714489 cites W2148603752 @default.
• W2951714489 cites W2152204644 @default.
• W2951714489 cites W2315159127 @default.
• W2951714489 cites W2566828246 @default.
• W2951714489 cites W2905404184 @default.
• W2951714489 cites W2963094815 @default.
• W2951714489 cites W3098272239 @default.
• W2951714489 cites W3099134300 @default.
• W2951714489 cites W3104887532 @default.
• W2951714489 cites W2154415584 @default.
• W2951714489 hasPublicationYear "2017" @default.
• W2951714489 type Work @default.
• W2951714489 sameAs 2951714489 @default.
• W2951714489 citedByCount "1" @default.
• W2951714489 countsByYear W29517144892020 @default.
• W2951714489 crossrefType "posted-content" @default.
• W2951714489 hasAuthorship W2951714489A5039021124 @default.
• W2951714489 hasAuthorship W2951714489A5076708141 @default.
• W2951714489 hasConcept C105795698 @default.
• W2951714489 hasConcept C119043178 @default.
• W2951714489 hasConcept C119340705 @default.
• W2951714489 hasConcept C121955636 @default.
• W2951714489 hasConcept C125112378 @default.
• W2951714489 hasConcept C144133560 @default.
• W2951714489 hasConcept C149782125 @default.
• W2951714489 hasConcept C154945302 @default.
• W2951714489 hasConcept C178650346 @default.
• W2951714489 hasConcept C196083921 @default.
• W2951714489 hasConcept C2776502983 @default.
• W2951714489 hasConcept C28826006 @default.
• W2951714489 hasConcept C33923547 @default.
• W2951714489 hasConcept C41008148 @default.
• W2951714489 hasConcept C48921125 @default.
• W2951714489 hasConcept C99656134 @default.
• W2951714489 hasConceptScore W2951714489C105795698 @default.
• W2951714489 hasConceptScore W2951714489C119043178 @default.
• W2951714489 hasConceptScore W2951714489C119340705 @default.
• W2951714489 hasConceptScore W2951714489C121955636 @default.
• W2951714489 hasConceptScore W2951714489C125112378 @default.
• W2951714489 hasConceptScore W2951714489C144133560 @default.
• W2951714489 hasConceptScore W2951714489C149782125 @default.
• W2951714489 hasConceptScore W2951714489C154945302 @default.
• W2951714489 hasConceptScore W2951714489C178650346 @default.
• W2951714489 hasConceptScore W2951714489C196083921 @default.
• W2951714489 hasConceptScore W2951714489C2776502983 @default.
• W2951714489 hasConceptScore W2951714489C28826006 @default.
• W2951714489 hasConceptScore W2951714489C33923547 @default.
• W2951714489 hasConceptScore W2951714489C41008148 @default.
• W2951714489 hasConceptScore W2951714489C48921125 @default.
• W2951714489 hasConceptScore W2951714489C99656134 @default.
• W2951714489 hasLocation W29517144891 @default.
• W2951714489 hasOpenAccess W2951714489 @default.
• W2951714489 hasPrimaryLocation W29517144891 @default.
• W2951714489 hasRelatedWork W14058067 @default.
• W2951714489 hasRelatedWork W1721639621 @default.
• W2951714489 hasRelatedWork W1784384189 @default.
• W2951714489 hasRelatedWork W1974931032 @default.
• W2951714489 hasRelatedWork W1989772712 @default.
• W2951714489 hasRelatedWork W2008520227 @default.
• W2951714489 hasRelatedWork W2040050598 @default.
• W2951714489 hasRelatedWork W2052827106 @default.
• W2951714489 hasRelatedWork W2061373113 @default.
• W2951714489 hasRelatedWork W2061405999 @default.
• W2951714489 hasRelatedWork W2089630199 @default.
• W2951714489 hasRelatedWork W2114475689 @default.
• W2951714489 hasRelatedWork W2318092476 @default.
• W2951714489 hasRelatedWork W2331882591 @default.
• W2951714489 hasRelatedWork W2948955561 @default.
• W2951714489 hasRelatedWork W2952034306 @default.
• W2951714489 hasRelatedWork W3011188130 @default.
• W2951714489 hasRelatedWork W3025496867 @default.
• W2951714489 hasRelatedWork W3183218284 @default.
• W2951714489 hasRelatedWork W3202537323 @default.
• W2951714489 isParatext "false" @default.
• W2951714489 isRetracted "false" @default.
• W2951714489 magId "2951714489" @default.

• next