Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386794611> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4386794611 abstract "Inference for prediction errors is critical in time series forecasting pipelines. However, providing statistically meaningful uncertainty intervals for prediction errors remains relatively under-explored. Practitioners often resort to forward cross-validation (FCV) for obtaining point estimators and constructing confidence intervals based on the Central Limit Theorem (CLT). The naive version assumes independence, a condition that is usually invalid due to time correlation. These approaches lack statistical interpretations and theoretical justifications even under stationarity. This paper systematically investigates uncertainty intervals for prediction errors in time series forecasting. We first distinguish two key inferential targets: the stochastic test error over near future data points, and the expected test error as the expectation of the former. The stochastic test error is often more relevant in applications needing to quantify uncertainty over individual time series instances. To construct prediction intervals for the stochastic test error, we propose the quantile-based forward cross-validation (QFCV) method. Under an ergodicity assumption, QFCV intervals have asymptotically valid coverage and are shorter than marginal empirical quantiles. In addition, we also illustrate why naive CLT-based FCV intervals fail to provide valid uncertainty intervals, even with certain corrections. For non-stationary time series, we further provide rolling intervals by combining QFCV with adaptive conformal prediction to give time-average coverage guarantees. Overall, we advocate the use of QFCV procedures and demonstrate their coverage and efficiency through simulations and real data examples." @default.
- W4386794611 created "2023-09-16" @default.
- W4386794611 creator A5021087479 @default.
- W4386794611 creator A5027340494 @default.
- W4386794611 creator A5056904374 @default.
- W4386794611 creator A5057257463 @default.
- W4386794611 creator A5057617652 @default.
- W4386794611 date "2023-09-14" @default.
- W4386794611 modified "2023-10-18" @default.
- W4386794611 title "Uncertainty Intervals for Prediction Errors in Time Series Forecasting" @default.
- W4386794611 doi "https://doi.org/10.48550/arxiv.2309.07435" @default.
- W4386794611 hasPublicationYear "2023" @default.
- W4386794611 type Work @default.
- W4386794611 citedByCount "0" @default.
- W4386794611 crossrefType "posted-content" @default.
- W4386794611 hasAuthorship W4386794611A5021087479 @default.
- W4386794611 hasAuthorship W4386794611A5027340494 @default.
- W4386794611 hasAuthorship W4386794611A5056904374 @default.
- W4386794611 hasAuthorship W4386794611A5057257463 @default.
- W4386794611 hasAuthorship W4386794611A5057617652 @default.
- W4386794611 hasBestOaLocation W43867946111 @default.
- W4386794611 hasConcept C103402496 @default.
- W4386794611 hasConcept C105795698 @default.
- W4386794611 hasConcept C118671147 @default.
- W4386794611 hasConcept C143724316 @default.
- W4386794611 hasConcept C149782125 @default.
- W4386794611 hasConcept C151406439 @default.
- W4386794611 hasConcept C151730666 @default.
- W4386794611 hasConcept C154945302 @default.
- W4386794611 hasConcept C185429906 @default.
- W4386794611 hasConcept C2776214188 @default.
- W4386794611 hasConcept C33923547 @default.
- W4386794611 hasConcept C41008148 @default.
- W4386794611 hasConcept C86803240 @default.
- W4386794611 hasConcept C87007009 @default.
- W4386794611 hasConceptScore W4386794611C103402496 @default.
- W4386794611 hasConceptScore W4386794611C105795698 @default.
- W4386794611 hasConceptScore W4386794611C118671147 @default.
- W4386794611 hasConceptScore W4386794611C143724316 @default.
- W4386794611 hasConceptScore W4386794611C149782125 @default.
- W4386794611 hasConceptScore W4386794611C151406439 @default.
- W4386794611 hasConceptScore W4386794611C151730666 @default.
- W4386794611 hasConceptScore W4386794611C154945302 @default.
- W4386794611 hasConceptScore W4386794611C185429906 @default.
- W4386794611 hasConceptScore W4386794611C2776214188 @default.
- W4386794611 hasConceptScore W4386794611C33923547 @default.
- W4386794611 hasConceptScore W4386794611C41008148 @default.
- W4386794611 hasConceptScore W4386794611C86803240 @default.
- W4386794611 hasConceptScore W4386794611C87007009 @default.
- W4386794611 hasLocation W43867946111 @default.
- W4386794611 hasOpenAccess W4386794611 @default.
- W4386794611 hasPrimaryLocation W43867946111 @default.
- W4386794611 hasRelatedWork W2065098330 @default.
- W4386794611 hasRelatedWork W2091563338 @default.
- W4386794611 hasRelatedWork W2114355762 @default.
- W4386794611 hasRelatedWork W2132618155 @default.
- W4386794611 hasRelatedWork W2302417351 @default.
- W4386794611 hasRelatedWork W2525669318 @default.
- W4386794611 hasRelatedWork W2627001344 @default.
- W4386794611 hasRelatedWork W3124911654 @default.
- W4386794611 hasRelatedWork W3137730994 @default.
- W4386794611 hasRelatedWork W4233086710 @default.
- W4386794611 isParatext "false" @default.
- W4386794611 isRetracted "false" @default.
- W4386794611 workType "article" @default.