A Note on the Finite Sample Bias in Time Series Cross-Validation

Amaze Lusompa

No RWP 25-17, Research Working Paper from Federal Reserve Bank of Kansas City

Abstract: It is well known that model selection via cross validation can be biased for time series models. However, many researchers have argued that this bias does not apply when using cross-validation with vector autoregressions (VAR) or with time series models whose errors follow a martingale-like structure. I show that even under these circumstances, performing cross-validation on time series data will still generate bias in general.

Keywords: time series; model selection; model validation; martingale (search for similar items in EconPapers)
JEL-codes: C10 C50 C52 (search for similar items in EconPapers)
Pages: 10
Date: 2025-11-24, Revised 2025-12-08
New Economics Papers: this item is included in nep-ecm and nep-ets
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.kansascityfed.org/research/research-wo ... es-cross-validation/ Full text (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:fip:fedkrw:102151

Ordering information: This working paper can be ordered from

DOI: 10.18651/RWP2025-17

Access Statistics for this paper

More papers in Research Working Paper from Federal Reserve Bank of Kansas City Contact information at EDIRC.
Bibliographic data for series maintained by Kira Lillard ().