Pandemic-proofing Out-of-sample Portfolio Evaluations

Hrishikesh Vinod

Fordham Economics Discussion Paper Series from Fordham University, Department of Economics

Abstract: Evaluation of the performance of portfolios and of various methods of ranking them has to be out-of-sample. Otherwise, selection methods that fit the past data best would always win. Suppose the time series chosen for out-of-sample evaluation happens to have any (upward, downward, zigzag) trend. In that case, portfolio selec- tion methods for that trend will work best but fail in general. We describe algorithms for the removal of such bias by using randomization. The R package 'generalCorr' has them. We use 169-month Dow Jones stock data to illustrate outOFsamp(), outOFsell().

Keywords: Portfolio; choice (search for similar items in EconPapers)
JEL-codes: C30 C51 (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://archive.fordham.edu/ECONOMICS_RESEARCH/PAPERS/dp2023_04_vinod.pdf (application/pdf)

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:frd:wpaper:dp2023-04er:dp2023-04

Access Statistics for this paper

More papers in Fordham Economics Discussion Paper Series from Fordham University, Department of Economics Contact information at EDIRC.
Bibliographic data for series maintained by Fordham Economics ().