Journal of East China Normal University(Natural Sc ›› 2012, Vol. 2012 ›› Issue (5): 76-84.

• Article • Previous Articles     Next Articles

Wavelet estimation for locally self-similar processes

LU Zhi-ping 1, TAO Qin-ying 2   

  1. 1. Research Center of International Finance and Risk Management, East China Normal University, Shanghai 200241, China; 2. Department of Mathematics, East China Normal University, Shanghai 200241, China
  • Received:2011-12-01 Revised:2012-03-01 Online:2012-09-25 Published:2012-09-29

Abstract: A new estimation method was proposed based on the maximal overlap discrete wavelet transform, which provided a good alternative for the estimation of the time-varying self-similarity parameters. It also included a simulation-based study using Monte Carlo method, which increases the accuracy of the estimation. Finally, an application was made on the vertical ocean shear measurements.

Key words: locally self-similar process, long memory, Monte Carlo simulation, OLS regression, wavelet transform

CLC Number: