The effect of noise reduction in measuring the linear and nonlinear dependency ...

• Author(s): Hossein, Hassani ; Dionísio, Andreia ; Ghodsi, Mansoureh
• Date: 2010
• Persistent ID: http://hdl.handle.net/10174/1820
• Origin: Repositório Científico da Universidade de Évora
• Subject(s): Measure of dependencies, Noise reduction ,Stock markets, Mutual information, Detrended fluctuation analysis, Detrended moving average method, Singular spectrum analysis, ARMA, GARCH
• Document Type: Article
• Language: English
• Editor(s): Elsevier

Description

The daily closing prices of several stock market indices are examined to analyse whether noise reduction matters in measuring dependencies of the financial series. We consider the effect of noise reduction on the linear and nonlinear measure of dependencies. We also use singular spectrum analysis as a powerful method for filtering financial series. We compare the results with those obtained by ARMA and GARCH models as linear and nonlinear methods for filtering the series. We also examine the findings on an artificial data set namely the Hénon map.