Identifying and Treating Outliers in Finance

Vincenzo Verardi, John Adams, Darren Hayunga, Sattar Mansi, David Reeb

Research output: Contribution to journalArticle

Abstract

Outliers represent a fundamental challenge in empirical finance research. We investigate whether the routine techniques used in finance research to identify and treat outliers are appropriate for the data structures we observe in practice. Specifically, we propose a multivariate identification strategy that can effectively detect outliers. We also introduce an estimator that minimizes the bias outliers cause in both cross-sectional and panel regressions and provide outlier mitigation guidance. Using replications of four recently published studies in premier finance journals, we show how adjusting for multivariate outliers can lead to significantly different results.
LanguageEnglish
Number of pages64
JournalFinancial Management
Publication statusPublished - 2019

Fingerprint

Outliers
Finance
Guidance
Estimator
Data structures
Replication
Cross-sectional regression
Mitigation
Panel regression

Keywords

  • outliers
  • univariate vs multivariate identification
  • robust regressions
  • winsorizing
  • trimming
  • bias

Cite this

Verardi, V., Adams, J., Hayunga, D., Mansi, S., & Reeb, D. (2019). Identifying and Treating Outliers in Finance. Financial Management.
Verardi, Vincenzo ; Adams, John ; Hayunga, Darren ; Mansi, Sattar ; Reeb, David. / Identifying and Treating Outliers in Finance. In: Financial Management. 2019.
@article{c09bd83407554eb3a75af18a732af569,
title = "Identifying and Treating Outliers in Finance",
abstract = "Outliers represent a fundamental challenge in empirical finance research. We investigate whether the routine techniques used in finance research to identify and treat outliers are appropriate for the data structures we observe in practice. Specifically, we propose a multivariate identification strategy that can effectively detect outliers. We also introduce an estimator that minimizes the bias outliers cause in both cross-sectional and panel regressions and provide outlier mitigation guidance. Using replications of four recently published studies in premier finance journals, we show how adjusting for multivariate outliers can lead to significantly different results.",
keywords = "outliers, univariate vs multivariate identification, robust regressions, winsorizing, trimming, bias",
author = "Vincenzo Verardi and John Adams and Darren Hayunga and Sattar Mansi and David Reeb",
year = "2019",
language = "English",
journal = "Financial Management",
issn = "1471-9185",
publisher = "Chartered Institute of Mangament Accoutants",

}

Verardi, V, Adams, J, Hayunga, D, Mansi, S & Reeb, D 2019, 'Identifying and Treating Outliers in Finance' Financial Management.

Identifying and Treating Outliers in Finance. / Verardi, Vincenzo; Adams, John; Hayunga, Darren; Mansi, Sattar; Reeb, David.

In: Financial Management, 2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Identifying and Treating Outliers in Finance

AU - Verardi, Vincenzo

AU - Adams, John

AU - Hayunga, Darren

AU - Mansi, Sattar

AU - Reeb, David

PY - 2019

Y1 - 2019

N2 - Outliers represent a fundamental challenge in empirical finance research. We investigate whether the routine techniques used in finance research to identify and treat outliers are appropriate for the data structures we observe in practice. Specifically, we propose a multivariate identification strategy that can effectively detect outliers. We also introduce an estimator that minimizes the bias outliers cause in both cross-sectional and panel regressions and provide outlier mitigation guidance. Using replications of four recently published studies in premier finance journals, we show how adjusting for multivariate outliers can lead to significantly different results.

AB - Outliers represent a fundamental challenge in empirical finance research. We investigate whether the routine techniques used in finance research to identify and treat outliers are appropriate for the data structures we observe in practice. Specifically, we propose a multivariate identification strategy that can effectively detect outliers. We also introduce an estimator that minimizes the bias outliers cause in both cross-sectional and panel regressions and provide outlier mitigation guidance. Using replications of four recently published studies in premier finance journals, we show how adjusting for multivariate outliers can lead to significantly different results.

KW - outliers

KW - univariate vs multivariate identification

KW - robust regressions

KW - winsorizing

KW - trimming

KW - bias

M3 - Article

JO - Financial Management

T2 - Financial Management

JF - Financial Management

SN - 1471-9185

ER -