FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3146796711> ?p ?o ?g. }

• W3146796711 endingPage "12" @default.
• W3146796711 startingPage "1" @default.
• W3146796711 abstract "Cross-validation is a widely-used technique to estimate prediction error, but its behavior is complex and not fully understood. Ideally, one would like to think that cross-validation estimates the prediction error for the model at hand, fit to the training data. We prove that this is not the case for the linear model fit by ordinary least squares; rather it estimates the average prediction error of models fit on other unseen training sets drawn from the same population. We further show that this phenomenon occurs for most popular estimates of prediction error, including data splitting, bootstrapping, and Mallow’s Cp . Next, the standard confidence intervals for prediction error derived from cross-validation may have coverage far below the desired level. Because each data point is used for both training and testing, there are correlations among the measured accuracies for each fold, and so the usual estimate of variance is too small. We introduce a nested cross-validation scheme to estimate this variance more accurately, and show empirically that this modification leads to intervals with approximately correct coverage in many examples where traditional cross-validation intervals fail. Lastly, our analysis also shows that when producing confidence intervals for prediction accuracy with simple data splitting, one should not re-fit the model on the combined data, since this invalidates the confidence intervals." @default.
• W3146796711 created "2021-04-13" @default.
• W3146796711 creator A5027340494 @default.
• W3146796711 creator A5045046961 @default.
• W3146796711 creator A5045744709 @default.
• W3146796711 date "2023-05-15" @default.
• W3146796711 modified "2023-10-03" @default.
• W3146796711 title "Cross-validation: what does it estimate and how well does it do it?" @default.
• W3146796711 cites W1502338185 @default.
• W3146796711 cites W1981251392 @default.
• W3146796711 cites W1995398986 @default.
• W3146796711 cites W2006676204 @default.
• W3146796711 cites W2018471882 @default.
• W3146796711 cites W2032481853 @default.
• W3146796711 cites W2033872649 @default.
• W3146796711 cites W2040615655 @default.
• W3146796711 cites W2050297026 @default.
• W3146796711 cites W2054640142 @default.
• W3146796711 cites W2112081648 @default.
• W3146796711 cites W2120199131 @default.
• W3146796711 cites W2142635246 @default.
• W3146796711 cites W2151699048 @default.
• W3146796711 cites W2162041430 @default.
• W3146796711 cites W2167277498 @default.
• W3146796711 cites W2168175751 @default.
• W3146796711 cites W2625919377 @default.
• W3146796711 cites W2787894218 @default.
• W3146796711 cites W2977961562 @default.
• W3146796711 cites W3012175154 @default.
• W3146796711 cites W3106889297 @default.
• W3146796711 cites W4246048519 @default.
• W3146796711 cites W4249991467 @default.
• W3146796711 cites W4250236131 @default.
• W3146796711 doi "https://doi.org/10.1080/01621459.2023.2197686" @default.
• W3146796711 hasPublicationYear "2023" @default.
• W3146796711 type Work @default.
• W3146796711 sameAs 3146796711 @default.
• W3146796711 citedByCount "16" @default.
• W3146796711 countsByYear W31467967112021 @default.
• W3146796711 countsByYear W31467967112023 @default.
• W3146796711 crossrefType "journal-article" @default.
• W3146796711 hasAuthorship W3146796711A5027340494 @default.
• W3146796711 hasAuthorship W3146796711A5045046961 @default.
• W3146796711 hasAuthorship W3146796711A5045744709 @default.
• W3146796711 hasBestOaLocation W31467967112 @default.
• W3146796711 hasConcept C103402496 @default.
• W3146796711 hasConcept C105795698 @default.
• W3146796711 hasConcept C11413529 @default.
• W3146796711 hasConcept C121955636 @default.
• W3146796711 hasConcept C144024400 @default.
• W3146796711 hasConcept C144133560 @default.
• W3146796711 hasConcept C149782125 @default.
• W3146796711 hasConcept C149923435 @default.
• W3146796711 hasConcept C167085575 @default.
• W3146796711 hasConcept C18747219 @default.
• W3146796711 hasConcept C196083921 @default.
• W3146796711 hasConcept C207609745 @default.
• W3146796711 hasConcept C27181475 @default.
• W3146796711 hasConcept C2908647359 @default.
• W3146796711 hasConcept C33923547 @default.
• W3146796711 hasConcept C41008148 @default.
• W3146796711 hasConcept C41426520 @default.
• W3146796711 hasConcept C44249647 @default.
• W3146796711 hasConcept C99656134 @default.
• W3146796711 hasConceptScore W3146796711C103402496 @default.
• W3146796711 hasConceptScore W3146796711C105795698 @default.
• W3146796711 hasConceptScore W3146796711C11413529 @default.
• W3146796711 hasConceptScore W3146796711C121955636 @default.
• W3146796711 hasConceptScore W3146796711C144024400 @default.
• W3146796711 hasConceptScore W3146796711C144133560 @default.
• W3146796711 hasConceptScore W3146796711C149782125 @default.
• W3146796711 hasConceptScore W3146796711C149923435 @default.
• W3146796711 hasConceptScore W3146796711C167085575 @default.
• W3146796711 hasConceptScore W3146796711C18747219 @default.
• W3146796711 hasConceptScore W3146796711C196083921 @default.
• W3146796711 hasConceptScore W3146796711C207609745 @default.
• W3146796711 hasConceptScore W3146796711C27181475 @default.
• W3146796711 hasConceptScore W3146796711C2908647359 @default.
• W3146796711 hasConceptScore W3146796711C33923547 @default.
• W3146796711 hasConceptScore W3146796711C41008148 @default.
• W3146796711 hasConceptScore W3146796711C41426520 @default.
• W3146796711 hasConceptScore W3146796711C44249647 @default.
• W3146796711 hasConceptScore W3146796711C99656134 @default.
• W3146796711 hasFunder F4320306076 @default.
• W3146796711 hasFunder F4320332161 @default.
• W3146796711 hasLocation W31467967111 @default.
• W3146796711 hasLocation W31467967112 @default.
• W3146796711 hasLocation W31467967113 @default.
• W3146796711 hasOpenAccess W3146796711 @default.
• W3146796711 hasPrimaryLocation W31467967111 @default.
• W3146796711 hasRelatedWork W1531052103 @default.
• W3146796711 hasRelatedWork W1986990433 @default.
• W3146796711 hasRelatedWork W1999377718 @default.
• W3146796711 hasRelatedWork W2023147183 @default.
• W3146796711 hasRelatedWork W2061902340 @default.
• W3146796711 hasRelatedWork W2075349916 @default.
• W3146796711 hasRelatedWork W2765228684 @default.
• W3146796711 hasRelatedWork W2981008242 @default.

• next