Bootstrapping Daily Returns

33 Pages Posted: 30 Nov 2013

See all articles by Colin Bowers

Colin Bowers

Macquarie University - Department of Economics

Christopher Heaton

Macquarie University - Department of Economics; UNSW Australia Business School, School of Economics

Date Written: November 29, 2013

Abstract

A daily log-return can be regarded as a test statistic - specifically the (unscaled) sample mean of a sequence of intraday random variables. We discuss sufficient conditions for a dependent bootstrap to consistently and non-parametrically estimate the entire distribution of this “test statistic”, up to, but not including, the location parameter. The method proposed is robust to market microstructure effects. There are many possible applications. In this paper, two are considered: 1) Estimating daily variance, and 2) Estimating Value-at-Risk (VaR). Of particular import: the VaR estimator is combined with the framework described in Patton & Li (2013) to produce forecast evaluation tests that are significantly more powerful than current popular techniques.

Keywords: Distribution of Returns, Bootstrap, Variance, Value-at-Risk, Intraday

JEL Classification: C13, C15, C51, C52, C53

Suggested Citation

Bowers, Colin and Heaton, Chris, Bootstrapping Daily Returns (November 29, 2013). Available at SSRN: https://ssrn.com/abstract=2361393 or http://dx.doi.org/10.2139/ssrn.2361393

Colin Bowers (Contact Author)

Macquarie University - Department of Economics ( email )

North Ryde
Sydney, New South Wales 2109
Australia

Chris Heaton

Macquarie University - Department of Economics ( email )

Sydney NSW 2109
Australia

UNSW Australia Business School, School of Economics

High Street
Sydney, NSW 2052
Australia

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
196
Abstract Views
1,543
Rank
279,781
PlumX Metrics