Skip navigation
Please use this identifier to cite or link to this item: http://repositorio.unb.br/handle/10482/42141
Files in This Item:
There are no files associated with this item.
Title: Using the Lévy sections to reduce risks in the buying strategies and asset sales that value in time
Authors: Figueiredo Neto, Annibal Dias de
Castro, Márcio Tavares de
Fonseca, Regina Célia Bueno da
Matsushita, Raul Yukihiro
Assunto:: Seções de Lévy
Compra e venda
Ativos financeiros
Issue Date: 2021
Publisher: Elsevier
Citation: FIGUEIREDO NETO, Annibal et al. Using the Lévy sections to reduce risks in the buying strategies and asset sales that value in time. Communications in Nonlinear Science and Numerical Simulation, v. 104, 106023, jan. 2022. DOI: https://doi.org/10.1016/j.cnsns.2021.106023.
Abstract: Previously, some of us put forward the Lévy sections theorem revisited as an extension of the classical central limit theorem that provides an alternative view of data volatilities (Figueiredo et al., 2007a, 2007b). In this paper, we discuss its usefulness in the risk assessment of financial assets. Although it is a stylized fact that prices are likely to follow non-Gaussian random walks, time randomization under the Lévy sections theorem conditions allows us to recover some Gaussianity. Thus, we propose a study comparing two buying and selling strategies: A fixed-time interval strategy against a random-time-interval strategy based on a Lévy section . We exemplify our approach with four financial time series (two daily and two intraday datasets), and we conclude that the random-time strategy offers a lower risk and a given expected gain in a shorter time than the fixed-time strategy.
DOI: https://doi.org/10.1016/j.cnsns.2021.106023
metadata.dc.relation.publisherversion: https://www.sciencedirect.com/science/article/pii/S100757042100335X?via%3Dihub
Appears in Collections:Artigos publicados em periódicos e afins

Show full item record " class="statisticsLink btn btn-primary" href="/jspui/handle/10482/42141/statistics">



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.