TY - GEN
T1 - Is PCA reliable for the analysis of fractional Brownian motion?
AU - Özkurt, Tolga Esat
AU - Akgül, Tayfun
PY - 2005
Y1 - 2005
N2 - Estimation of the self-similarity parameter, also known as Hurst (H) parameter, is an important issue. In this paper, we study one of the H parameter estimation methods, namely the Principal Component Analysis (PCA) and show that this method may not give reliable results for the persistent part (H>0.5) of the fractional Brownian motion. Moreover, when the results are unreliable, the eigenvalue progression seriously deviates from linearity. Thus, with a linear-fit error threshold, one can comment on the reliability for the results of the PCA method.
AB - Estimation of the self-similarity parameter, also known as Hurst (H) parameter, is an important issue. In this paper, we study one of the H parameter estimation methods, namely the Principal Component Analysis (PCA) and show that this method may not give reliable results for the persistent part (H>0.5) of the fractional Brownian motion. Moreover, when the results are unreliable, the eigenvalue progression seriously deviates from linearity. Thus, with a linear-fit error threshold, one can comment on the reliability for the results of the PCA method.
UR - http://www.scopus.com/inward/record.url?scp=84863680222&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84863680222
SN - 1604238216
SN - 9781604238211
T3 - 13th European Signal Processing Conference, EUSIPCO 2005
SP - 1620
EP - 1623
BT - 13th European Signal Processing Conference, EUSIPCO 2005
T2 - 13th European Signal Processing Conference, EUSIPCO 2005
Y2 - 4 September 2005 through 8 September 2005
ER -