Show Less

Statistical Inference in Multifractal Random Walk Models for Financial Time Series


Cristina Sattarhoff

The dynamics of financial returns varies with the return period, from high-frequency data to daily, quarterly or annual data. Multifractal Random Walk models can capture the statistical relation between returns and return periods, thus facilitating a more accurate representation of real price changes. This book provides a generalized method of moments estimation technique for the model parameters with enhanced performance in finite samples, and a novel testing procedure for multifractality. The resource-efficient computer-based manipulation of large datasets is a typical challenge in finance. In this connection, this book also proposes a new algorithm for the computation of heteroscedasticity and autocorrelation consistent (HAC) covariance matrix estimators that can cope with large datasets.


Show Summary Details
Restricted access

List of symbols 11


List of symbols bN bandwidth C (c) circulant matrix with the first column c dB (u) White Noise process in continuous time d mean distance d2 mean square distance f moments function f∗ the moments function in Bacry et al. (2008a, 2008b) F matrix of sample moments F (j : k) matrix containing rows j till k of F Ft public information at time t F ∗ extended matrix of sample moments, employed in the HAC algorithm introduced in this thesis F ∗j the jth column in matrix F ∗ h lag of the autocorrelation/autocovariance function i index j index k index k the number of volatility components in the MSM model ℓ sampling interval L variable employed in the HAC estimation algorithms mµ an MRW average employed in the multifractality test 12 List of symbols mσ an MRW average employed in the multifractality test M multifactality test statistic M (q, τ) empirical qth order absolute moment of returns with period τ N cascade step; sample size Pt price at time t q moment order; number of moment conditions employed in the GMM estimation Q set containing the finite moment orders q QN (θ) objective function in the GMM estimation rt returns between t− 1 and t in the classic financial volatility models r (dt,N) returns in dt at cascade step N r (t) returns between t− 1 and t in MV models r (t, ℓ) returns between t− 1 and t with sampling interval ℓ in MV models S asymptotic covariance matrix of the normalized sample mean...

You are not authenticated to view the full text of this chapter or article.

This site requires a subscription or purchase to access the full text of books or journals.

Do you have any questions? Contact us.

Or login to access all content.