On the number of outliers in data from a linear model.

Freeman, Peter R.. "On the number of outliers in data from a linear model.." Trabajos de Estadística e Investigación Operativa 31.1 (1980): 349-365. <http://eudml.org/doc/40833>.

@article{Freeman1980,
abstract = {This paper reviews models for the occurrence of outliers in data from the linear model. The Bayesian analyses are all closely similar in form, but differ in the way they treat suspected outliers. The models are compared on Darwin's data and one of them is used on data from a 25 factorial experiment.The question on how many outliers are present involves comparison of models with different number of parameters. A solution using proper priors on all parameters is given. On two trial datasets it is found insensitive to choice of priors on all except the parameters representing the amount of contamination in the outliers. Here, choice of even a slightly wrong prior can be very misleading. Moreover, it is difficult to choose an appropriate prior when contaminations can be both positive or negative.},
author = {Freeman, Peter R.},
journal = {Trabajos de Estadística e Investigación Operativa},
keywords = {Análisis bayesiano; Observaciones anómalas; Modelos lineales; Distribuciones a priori},
language = {eng},
number = {1},
pages = {349-365},
title = {On the number of outliers in data from a linear model.},
url = {http://eudml.org/doc/40833},
volume = {31},
year = {1980},
}

TY - JOUR
AU - Freeman, Peter R.
TI - On the number of outliers in data from a linear model.
JO - Trabajos de Estadística e Investigación Operativa
PY - 1980
VL - 31
IS - 1
SP - 349
EP - 365
AB - This paper reviews models for the occurrence of outliers in data from the linear model. The Bayesian analyses are all closely similar in form, but differ in the way they treat suspected outliers. The models are compared on Darwin's data and one of them is used on data from a 25 factorial experiment.The question on how many outliers are present involves comparison of models with different number of parameters. A solution using proper priors on all parameters is given. On two trial datasets it is found insensitive to choice of priors on all except the parameters representing the amount of contamination in the outliers. Here, choice of even a slightly wrong prior can be very misleading. Moreover, it is difficult to choose an appropriate prior when contaminations can be both positive or negative.
LA - eng
KW - Análisis bayesiano; Observaciones anómalas; Modelos lineales; Distribuciones a priori
UR - http://eudml.org/doc/40833
ER -