Optimal Portfolio Size under Parameter Uncertainty

Rodolphe Vanderveken (), Nathan Lassance () and Frédéric Vrins ()
Additional contact information
Rodolphe Vanderveken: Université catholique de Louvain, LIDAM/LFIN, Belgium
Nathan Lassance: Université catholique de Louvain, LIDAM/LFIN, Belgium
Frédéric Vrins: Université catholique de Louvain, LIDAM/LFIN, Belgium

No 2024004, LIDAM Discussion Papers LFIN from Université catholique de Louvain, Louvain Finance (LFIN)

Abstract: Estimation risk in portfolio selection can be mitigated with sparse approaches such as lasso that penalizes for the norm of the portfolio weights and excludes assets from the investment universe. The latter are revealed a posteriori, by identifying which assets receive an optimal weight of zero. We show instead that in the presence of parameter uncertainty, it is desirable to remove assets before computing the portfolio weights. In particular, we show that the optimal portfolio size strikes a tradeoff between accessing additional investment opportunities and limiting estimation risk. Our approach disentangles the determination of the optimal portfolio size from the asset selection rule, making it more easily implementable and robust to estimation risk than alternative sparse methods. Empirically, our restricted portfolios substantially outperform their counterparts applied to all available assets. Our methodology renders portfolio theory valuable even when the full dataset dimension is comparable to the sample size.

Keywords: Portfolio selection; estimation risk; dimension reduction; out-of-sample performance; portfolio combination rules (search for similar items in EconPapers)
JEL-codes: G11 G12 (search for similar items in EconPapers)
Pages: 80
Date: 2024-07-05
New Economics Papers: this item is included in nep-rmg
References: Add references at CitEc
Citations:

Downloads: (external link)
https://dial.uclouvain.be/pr/boreal/en/object/bore ... tastream/PDF_01/view (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:ajf:louvlf:2024004

Access Statistics for this paper

More papers in LIDAM Discussion Papers LFIN from Université catholique de Louvain, Louvain Finance (LFIN) Voie du Roman Pays 34, 1348 Louvain-la-Neuve (Belgium). Contact information at EDIRC.
Bibliographic data for series maintained by Séverine De Visscher ().