Skip to Main content Skip to Navigation
Conference papers

The Replacement Bootstrap for Dependent Data

Amir Sani 1 Alessandro Lazaric 1 Daniil Ryabko 1
1 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : Applications that deal with time-series data often require evaluating complex statistics for which each time series is essentially one data point. When only a few time series are available, bootstrap methods are used to generate additional samples that can be used to evaluate empirically the statistic of interest. In this work a novel bootstrap method is proposed, which is shown to have some asymptotic consistency guarantees under the only assumption that the time series are stationary and ergodic. This contrasts previously available results that impose mixing or finite-memory assumptions on the data. Empirical evaluation on simulated and real data, using a practically relevant and complex extrema statistic is provided.
Complete list of metadata

Cited literature [22 references]  Display  Hide  Download
Contributor : Alessandro Lazaric <>
Submitted on : Tuesday, May 26, 2015 - 4:56:51 PM
Last modification on : Friday, December 11, 2020 - 6:44:05 PM
Long-term archiving on: : Monday, April 24, 2017 - 3:27:29 PM


Files produced by the author(s)


  • HAL Id : hal-01144547, version 1


Amir Sani, Alessandro Lazaric, Daniil Ryabko. The Replacement Bootstrap for Dependent Data. Proceedings of the IEEE International Symposium on Information Theory, Jun 2015, Hong Kong, Hong Kong SAR China. ⟨hal-01144547⟩



Record views


Files downloads