SSA NSW Branch: Sieve bootstrap memory parameter in long-range dependent stationary functional time series by Prof. Hanlin Shang

This month we are very pleased to have Prof. Hanlin Shang from Macquarie University to present his recent work about sieve bootstrap and functional time series.
 

Please note for security reasons, you will need to register in advance for this meeting: https://macquarie.zoom.us/meeting/register/tZEvceuhrT0tE9PY0vtRKVWW8LNbX0hMmBsg

After registering, you will receive a confirmation email containing information about joining the meeting.

Any questions, please feel free to contact: secretary.nswbranch@statsoc.org.au

Date: Wednesday, 29th September 2021

Time: 6:00pm - 7:00pm (AEST)

Prof. Hanlin Shang
Macquarie University, Sydney

Sieve bootstrap memory parameter in long-range dependent stationary functional time series

Abstract:
We apply a sieve bootstrap procedure to quantify estimation uncertainty of long-memory parameter in stationary functional time series. To estimate the long-memory parameter, we use a semiparametric local Whittle estimator, where discrete Fourier transform and periodogram are constructed from the first set of principal component scores, via a functional principal component analysis. The sieve bootstrap procedure uses a general vector autoregressive representation of the estimated principal component scores. It generates bootstrap replicates that adequately mimic the dependence structure of the underlying stationary process. For each bootstrap replicate, we first compute the estimated first set of principal component scores and then apply the semiparametric local Whittle estimator to estimate the memory parameter. By taking quantiles of the estimated memory parameters from these bootstrap replicates, we can construct confidence intervals of the long-memory parameter. As measured by coverage probability differences between the empirical and nominal coverage probabilities at three levels of significance, we demonstrate the advantage of using the sieve bootstrap in comparison to the asymptotic confidence intervals based on normality.

Biography:
Hanlin is a Professor of Business Analytics at the Department of Actuarial Studies and Business Analytics, Macquarie University. Hanlin’s research interests include inference, modelling and forecasting functional time series.