Time Series Experiments and Causal Estimands: Exact Randomization Tests and Trading

42 Pages Posted: 26 Jun 2017 Last revised: 19 Jul 2017

See all articles by Iavor Bojinov

Iavor Bojinov

Harvard University, Department of Statistics, Students

Neil Shephard

Harvard University

Date Written: July 18, 2017

Abstract

We define causal estimands for experiments on single time series, extending the potential outcome framework to dealing with temporal data. Our approach allows the estimation of some of these estimands and exact randomization based p-values for testing causal effects, without imposing stringent assumptions. We test our methodology on simulated "potential autoregressions," which have a causal interpretation. Our methodology is partially inspired by data from a large number of experiments carried out by a financial company who compared the impact of two different ways of trading equity futures contracts. We use our methodology to make causal statements about their trading methods.

Keywords: Causality, potential outcomes, trading costs, non-parametric, randomization

JEL Classification: C01, C14, C22, C58

Suggested Citation

Bojinov, Iavor and Shephard, Neil, Time Series Experiments and Causal Estimands: Exact Randomization Tests and Trading (July 18, 2017). Available at SSRN: https://ssrn.com/abstract=2991825 or http://dx.doi.org/10.2139/ssrn.2991825

Iavor Bojinov

Harvard University, Department of Statistics, Students ( email )

Cambridge, MA
United States

Neil Shephard (Contact Author)

Harvard University ( email )

1875 Cambridge Street
Cambridge, MA 02138
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
78
Abstract Views
585
rank
324,550
PlumX Metrics