2019
DOI: 10.1111/fima.12269
|View full text |Cite
|
Sign up to set email alerts
|

Identifying and treating outliers in finance

Abstract: Outliers represent a fundamental challenge in the 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 caused in both cross‐sectional and panel regressions and provide outlier mitigation guidance. Using repli… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
28
0
4

Year Published

2020
2020
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 62 publications
(33 citation statements)
references
References 87 publications
(251 reference statements)
1
28
0
4
Order By: Relevance
“…This is so as the values of skewness, kurtosis and Jaque-Bera have confirmed so as presented earlier. This finding is not far from the truth as it concurs with both [93,94] findings. Data being not normally distributed can be due to data can never be normal because of asymmetries, discreteness, boundedness and existence of outliers.…”
Section: Resultssupporting
confidence: 82%
“…This is so as the values of skewness, kurtosis and Jaque-Bera have confirmed so as presented earlier. This finding is not far from the truth as it concurs with both [93,94] findings. Data being not normally distributed can be due to data can never be normal because of asymmetries, discreteness, boundedness and existence of outliers.…”
Section: Resultssupporting
confidence: 82%
“…These parameters are statistically significant at the 1% level, with the Table 1. The data were winsorized at the 1% and 99% percentiles (Adams et al 2019;Tukey 1962). The AIC and BIC tests confirmed that winsorized data explain better the models models explaining around 60% of variance.…”
Section: Regression Resultsmentioning
confidence: 87%
“…We winsorized the data at the 1% and 99% percentiles to minimize the potential effect of outliers (Tukey 1962). A recent review of financial studies shows that the majority of financial studies use winsorizing to treat outliers (Adams et al 2019).…”
Section: Datamentioning
confidence: 99%
See 1 more Smart Citation
“…One of these patterns results from the presence of outliers, defined as abnormal values that can have an extreme effect on the analysis (Acock, 2014;Irizarry & Love, 2015). It is not always easy to identify these outliers correctly, nor to estimate their real influence on data behavior (Adams, Hayunga, Mansi, Reeb, & Verardi, 2019;Loperfido, 2020). For this reason, researchers often follow protocols that recommend excluding these outliers, treating them as a problem to be solved before starting the core of the analysis (Hair, Black, Babin, & Anderson, 2018;Malhotra, 2018).…”
Section: Introduction Introductionmentioning
confidence: 99%