Examinando por Materia "Matriz de covarianza"
Mostrando 1 - 3 de 3
Resultados por página
Opciones de ordenación
Ítem ¿Agrega valor el uso de la metodología Shrinkage en la estimación de la matriz de covarianzas para el mercado accionario colombiano?(Universidad EAFIT, 2019) Herrera Passos, Tomás; Agudelo Rueda, Diego AlonsoThis article proposes to estimate the covariance matrix of stock returns in Colombian case by an optimally weighted average of two existing estimators the sample covariance matrix and singleindex covariance matrix proposed by Sharpe (1963) following the methodology of Ledoit and Wolf (2003). This method is generally known as Shrinkage, it is standard in decision theory and in empirical Bayesian statistics and allows to improve the calculation of the central values of the estimate. In this case we analyze this methodology for Colombian stocks returns listed at BVC (Bolsa de Valores de Colombia) and participants in the COLCAP composition from January 15, 2008 to May 2, 2019. We have found that the sample covariance matrix is superior in estimating risk than the structural methodology (based on Single Index Model) and Shrinkage, in any type of portfolio composition. However, when estimating the covariance matrix through the Shrinkage methodology in the portfolios of minimum risk and equally weighted have been observed a performance practically equal to the conventional (sample) methodology.Ítem Integración de estimadores robustos y no-paramétricos de dispersión en el clasificador LDA para monitoreo de riesgo crediticio(Universidad EAFIT, 2024) Arcia Hernández, Jesús Alberto; Ortiz Arias, SantiagoÍtem Precision Matrix Estimation using Preconditioned Conjugate Gradient with Regularization(Universidad EAFIT, 2024) Barrientos Osorio, Alejandro; Ortiz Arias, Santiago