The Feller diffusion, filter rules and abnormal stock returns

Paul Docherty, Yizhe Dong, Xiaojing Song, Mark Tippett

Research output: Contribution to journalArticle

1 Citation (Scopus)
3 Downloads (Pure)

Abstract

We determine the conditional expected logarithmic (that is, continuously compounded) return on a stock whose price evolves in terms of the Feller diffusion and then use it to demonstrate how one must know the exact probability density that describes a stock’s return before one can determine the correct way to calculate the abnormal returns that accrue on the stock. We show in particular that misspecification of the stochastic process which generates a stock’s price will lead to systematic biases in the abnormal returns calculated on the stock. We examine the implications this has for the proper conduct of empirical work and for the evaluation of stock and portfolio performance.
Original languageEnglish
Pages (from-to)426-438
Number of pages13
JournalEuropean Journal of Finance
Volume24
Issue number5
Early online date5 Apr 2017
DOIs
Publication statusPublished - 2018

Fingerprint

Filter
Abnormal returns
Stock prices
Stock returns
Stochastic processes
Portfolio performance
Stock performance
Misspecification
Evaluation

Keywords

  • Feller diffusion
  • Fokker-Planck equation
  • Geometric Brownian Motion
  • Logarithmic return

ASJC Scopus subject areas

  • Economics, Econometrics and Finance(all)

Cite this

The Feller diffusion, filter rules and abnormal stock returns. / Docherty, Paul; Dong, Yizhe; Song, Xiaojing; Tippett, Mark.

In: European Journal of Finance, Vol. 24, No. 5, 2018, p. 426-438.

Research output: Contribution to journalArticle

Docherty, Paul ; Dong, Yizhe ; Song, Xiaojing ; Tippett, Mark. / The Feller diffusion, filter rules and abnormal stock returns. In: European Journal of Finance. 2018 ; Vol. 24, No. 5. pp. 426-438.
@article{a42121fc89874faa9c4160d157e04fea,
title = "The Feller diffusion, filter rules and abnormal stock returns",
abstract = "We determine the conditional expected logarithmic (that is, continuously compounded) return on a stock whose price evolves in terms of the Feller diffusion and then use it to demonstrate how one must know the exact probability density that describes a stock’s return before one can determine the correct way to calculate the abnormal returns that accrue on the stock. We show in particular that misspecification of the stochastic process which generates a stock’s price will lead to systematic biases in the abnormal returns calculated on the stock. We examine the implications this has for the proper conduct of empirical work and for the evaluation of stock and portfolio performance.",
keywords = "Feller diffusion, Fokker-Planck equation, Geometric Brownian Motion, Logarithmic return",
author = "Paul Docherty and Yizhe Dong and Xiaojing Song and Mark Tippett",
note = "Acknowledgements The authors acknowledge the helpful comments and suggestions of the Editor and referee. The usual disclaimer applies.",
year = "2018",
doi = "10.1080/1351847X.2017.1309328",
language = "English",
volume = "24",
pages = "426--438",
journal = "European Journal of Finance",
issn = "1351-847X",
publisher = "Routledge",
number = "5",

}

TY - JOUR

T1 - The Feller diffusion, filter rules and abnormal stock returns

AU - Docherty, Paul

AU - Dong, Yizhe

AU - Song, Xiaojing

AU - Tippett, Mark

N1 - Acknowledgements The authors acknowledge the helpful comments and suggestions of the Editor and referee. The usual disclaimer applies.

PY - 2018

Y1 - 2018

N2 - We determine the conditional expected logarithmic (that is, continuously compounded) return on a stock whose price evolves in terms of the Feller diffusion and then use it to demonstrate how one must know the exact probability density that describes a stock’s return before one can determine the correct way to calculate the abnormal returns that accrue on the stock. We show in particular that misspecification of the stochastic process which generates a stock’s price will lead to systematic biases in the abnormal returns calculated on the stock. We examine the implications this has for the proper conduct of empirical work and for the evaluation of stock and portfolio performance.

AB - We determine the conditional expected logarithmic (that is, continuously compounded) return on a stock whose price evolves in terms of the Feller diffusion and then use it to demonstrate how one must know the exact probability density that describes a stock’s return before one can determine the correct way to calculate the abnormal returns that accrue on the stock. We show in particular that misspecification of the stochastic process which generates a stock’s price will lead to systematic biases in the abnormal returns calculated on the stock. We examine the implications this has for the proper conduct of empirical work and for the evaluation of stock and portfolio performance.

KW - Feller diffusion

KW - Fokker-Planck equation

KW - Geometric Brownian Motion

KW - Logarithmic return

U2 - 10.1080/1351847X.2017.1309328

DO - 10.1080/1351847X.2017.1309328

M3 - Article

VL - 24

SP - 426

EP - 438

JO - European Journal of Finance

JF - European Journal of Finance

SN - 1351-847X

IS - 5

ER -