A Unifying Model for Statistical Arbitrage: Model Assumptions and Empirical Failure

Research output: Contribution to journalArticlepeer-review

Standard Standard

A Unifying Model for Statistical Arbitrage: Model Assumptions and Empirical Failure. / Stephenson, Jeffrey; Vanstone, Bruce J; Hahn, Tobias.
In: Computational Economics, Vol. 58, No. 4, 12.2021, p. 943-964.

Research output: Contribution to journalArticlepeer-review

HarvardHarvard

APA

CBE

MLA

VancouverVancouver

Stephenson J, Vanstone BJ, Hahn T. A Unifying Model for Statistical Arbitrage: Model Assumptions and Empirical Failure. Computational Economics. 2021 Dec;58(4):943-964. Epub 2020 Apr 4. doi: 10.1007/s10614-020-09980-6

Author

Stephenson, Jeffrey ; Vanstone, Bruce J ; Hahn, Tobias. / A Unifying Model for Statistical Arbitrage: Model Assumptions and Empirical Failure. In: Computational Economics. 2021 ; Vol. 58, No. 4. pp. 943-964.

RIS

TY - JOUR

T1 - A Unifying Model for Statistical Arbitrage: Model Assumptions and Empirical Failure

AU - Stephenson, Jeffrey

AU - Vanstone, Bruce J

AU - Hahn, Tobias

PY - 2021/12

Y1 - 2021/12

N2 - Statistical arbitrage refers to a suite of quantitative investment strategies employed chiefly by hedge funds and proprietary trading firms. The arbitrageur can draw on a number of different approaches to identify and exploit an arbitrage opportunity, though the literature is broadly segmented by the canonical distance, cointegration and time series perspectives. Since the initial academic investigation of statistical arbitrage, its profitability has continued to diminish thanks largely to the increasing proportion of non-convergent opportunities. This paper surveys the existing literature, with particular emphasis given to evidence of statistical arbitrage failure, before unifying the distance, cointegration and time series perspectives under a single explicit model. The failure of statistical arbitrage opportunities is shown to be the direct consequence of implicit model assumptions that are inconsistent with the empirical literature. An alternative model is proposed, and evidence of its relative performance discussed.

AB - Statistical arbitrage refers to a suite of quantitative investment strategies employed chiefly by hedge funds and proprietary trading firms. The arbitrageur can draw on a number of different approaches to identify and exploit an arbitrage opportunity, though the literature is broadly segmented by the canonical distance, cointegration and time series perspectives. Since the initial academic investigation of statistical arbitrage, its profitability has continued to diminish thanks largely to the increasing proportion of non-convergent opportunities. This paper surveys the existing literature, with particular emphasis given to evidence of statistical arbitrage failure, before unifying the distance, cointegration and time series perspectives under a single explicit model. The failure of statistical arbitrage opportunities is shown to be the direct consequence of implicit model assumptions that are inconsistent with the empirical literature. An alternative model is proposed, and evidence of its relative performance discussed.

KW - Statistical arbitrage

KW - Pairs trading

KW - Spread trading

KW - Relative-value arbitrage

KW - Mean-reversion

U2 - 10.1007/s10614-020-09980-6

DO - 10.1007/s10614-020-09980-6

M3 - Article

VL - 58

SP - 943

EP - 964

JO - Computational Economics

JF - Computational Economics

SN - 1572-9974

IS - 4

ER -