Confirmation of multiple outliers in generalized linear and nonlinear regressions

Andy H. Lee; Wing K. Fung

doi:https://doi.org/10.1016/S0167-9473(96)00086-2

Confirmation of multiple outliers in generalized linear and nonlinear regressions

Andy H. Lee, Wing K. Fung

Research output: Contribution to journal › Comment/debate

Abstract

We propose a stepwise procedure for the detection of multiple outliers in generalized linear models and nonlinear regressions. The algorithm starts with a high breakdown point estimation method to find the potential outliers, then uses an adding-back iterative approach to confirm such outliers with envelopes derived from simulation. The proposed method can overcome the masking and swamping problems commonly occurred in multiple outliers detection. We apply the procedure to two real examples, and satisfactory results are obtained.

Original language	English
Pages (from-to)	55-65
Number of pages	11
Journal	Computational Statistics and Data Analysis
Volume	25
Issue number	1
DOIs	https://doi.org/10.1016/S0167-9473(96)00086-2
Publication status	Published - 1997

Access to Document

https://doi.org/10.1016/S0167-9473(96)00086-2

Cite this

@article{8e9c21deb0494008b5b163918e5deb4d,

title = "Confirmation of multiple outliers in generalized linear and nonlinear regressions",

abstract = "We propose a stepwise procedure for the detection of multiple outliers in generalized linear models and nonlinear regressions. The algorithm starts with a high breakdown point estimation method to find the potential outliers, then uses an adding-back iterative approach to confirm such outliers with envelopes derived from simulation. The proposed method can overcome the masking and swamping problems commonly occurred in multiple outliers detection. We apply the procedure to two real examples, and satisfactory results are obtained.",

keywords = "Generalized linear model, High breakdown methods, Multiple outliers, Nonlinear regression, Simulated envelopes",

author = "Lee, {Andy H.} and Fung, {Wing K.}",

year = "1997",

doi = "https://doi.org/10.1016/S0167-9473(96)00086-2",

language = "English",

volume = "25",

pages = "55--65",

journal = "Computational Statistics and Data Analysis",

issn = "0167-9473",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Confirmation of multiple outliers in generalized linear and nonlinear regressions

AU - Lee, Andy H.

AU - Fung, Wing K.

PY - 1997

Y1 - 1997

N2 - We propose a stepwise procedure for the detection of multiple outliers in generalized linear models and nonlinear regressions. The algorithm starts with a high breakdown point estimation method to find the potential outliers, then uses an adding-back iterative approach to confirm such outliers with envelopes derived from simulation. The proposed method can overcome the masking and swamping problems commonly occurred in multiple outliers detection. We apply the procedure to two real examples, and satisfactory results are obtained.

AB - We propose a stepwise procedure for the detection of multiple outliers in generalized linear models and nonlinear regressions. The algorithm starts with a high breakdown point estimation method to find the potential outliers, then uses an adding-back iterative approach to confirm such outliers with envelopes derived from simulation. The proposed method can overcome the masking and swamping problems commonly occurred in multiple outliers detection. We apply the procedure to two real examples, and satisfactory results are obtained.

KW - Generalized linear model

KW - High breakdown methods

KW - Multiple outliers

KW - Nonlinear regression

KW - Simulated envelopes

U2 - https://doi.org/10.1016/S0167-9473(96)00086-2

DO - https://doi.org/10.1016/S0167-9473(96)00086-2

M3 - Comment/debate

VL - 25

SP - 55

EP - 65

JO - Computational Statistics and Data Analysis

JF - Computational Statistics and Data Analysis

SN - 0167-9473

IS - 1

ER -

Confirmation of multiple outliers in generalized linear and nonlinear regressions

Abstract

Access to Document

Fingerprint

Cite this