Department of Economics and Business Economics

Bootstrap inference for pre-averaged realized volatility based on nonoverlapping returns

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

  • Sílvia Gonçalves, HEC Montréal (Université de Montréal), Canada
  • Ulrich Hounyo
  • Nour Meddahi, Toulouse School of Economics, France

The main contribution of this article is to propose bootstrap methods for realized volatility-like estimators defined on pre-averaged returns. In particular, we focus on the pre-averaged realized volatility estimator proposed by Podolskij and Vetter (2009). This statistic can be written (up to a bias correction term) as the (scaled) sum of squared preaveraged returns, where the pre-averaging is done over all possible nonoverlapping blocks of consecutive observations. Pre-averaging reduces the influence of the noise and allows for realized volatility estimation on the pre-averaged returns. The nonoverlapping nature of the pre-averaged returns implies that these are asymptotically uncorrelated, but possibly heteroskedastic. This motivates the application of the wild bootstrap in this context. We provide a proof of the firstorder asymptotic validity of this method for percentile and percentile-t intervals. Our Monte Carlo simulations show that the wild bootstrap can improve the finite sample properties of the existing first-order asymptotic theory provided we choose the external random variable appropriately. We use empirical work to illustrate its use in practice.

Original languageEnglish
Article numbernbu011
JournalJournal of Financial Econometrics
Pages (from-to)679-707
Number of pages29
Publication statusPublished - 1 Jan 2014

    Research areas

  • High-frequency data, Market microstructure noise, Pre-averaging, Realized volatility, Wild bootstrap

See relations at Aarhus University Citationformats

ID: 85206502