Persistence detection for the application of a complex algorithm in volatility prediction

• Autores: Briones Zúñiga, José Luis, Arancel Llerena, Felipe Fernando
• Formato: objeto de conferencia
• Fecha de Publicación: 2022
• Institución: Universidad Tecnológica del Perú
• Repositorio: UTP-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorio.utp.edu.pe:20.500.12867/6369
• Enlace del recurso: https://hdl.handle.net/20.500.12867/6369
• Nivel de acceso: acceso abierto
• Materia: Exchange rate; Econometrics; https://purl.org/pe-repo/ocde/ford#5.02.02

The research studies the dynamics of the volatility of the nominal exchange rate of the Peruvian nuevo sol against the US dollar, with the aim of identifying signs of dependencies over long time distances. The existence of persistence in the increases in yields and the volatility process is explored by applying two tests based on periodograms, the Hurst exponent is estimated, its consistency over time and the graphical analysis of its distributions for the subsequent application of the algorithm of complex dynamics. For this objective, the time series of the nominal exchange rate of the nuevo sol against the dollar from January 3, 2013 to February 11, 2021 is used. A nongeometric decay was identified in the correlograms in its nonlinear transformation and estimates of the fractional integration parameter d > 0 together with the empirical and rescaled Hurst estimates H > 0.5, therefore it is concluded that there is sufficient evidence of a non-random fractal pattern conducive to the use of the complex algorithm in process.