Assessing influence in survival data with a cured fraction and covariates.

Ortega, Edwin M. M., Cancho, Vicente G., and Lachos, Victor Hugo. "Assessing influence in survival data with a cured fraction and covariates.." SORT 32.2 (2008): 115-140. <http://eudml.org/doc/42044>.

@article{Ortega2008,
abstract = {Diagnostic methods have been an important tool in regression analysis to detect anomalies, such as departures from error assumptions and the presence of outliers and influential observations with the fitted models. Assuming censored data, we considered a classical analysis and Bayesian analysis assuming no informative priors for the parameters of the model with a cure fraction. A Bayesian approach was considered by using Markov Chain Monte Carlo Methods with Metropolis-Hasting algorithms steps to obtain the posterior summaries of interest. Some influence methods, such as the local influence, total local influence of an individual, local influence on predictions and generalized leverage were derived, analyzed and discussed in survival data with a cure fraction and covariates. The relevance of the approach was illustrated with a real data set, where it is shown that, by removing the most influential observations, the decision about which model best fits the data is changed.},
author = {Ortega, Edwin M. M., Cancho, Vicente G., Lachos, Victor Hugo},
journal = {SORT},
keywords = {cure fraction; Bayesian inference; local influence; generalized leverage; survival data},
language = {eng},
number = {2},
pages = {115-140},
title = {Assessing influence in survival data with a cured fraction and covariates.},
url = {http://eudml.org/doc/42044},
volume = {32},
year = {2008},
}

TY - JOUR
AU - Ortega, Edwin M. M.
AU - Cancho, Vicente G.
AU - Lachos, Victor Hugo
TI - Assessing influence in survival data with a cured fraction and covariates.
JO - SORT
PY - 2008
VL - 32
IS - 2
SP - 115
EP - 140
AB - Diagnostic methods have been an important tool in regression analysis to detect anomalies, such as departures from error assumptions and the presence of outliers and influential observations with the fitted models. Assuming censored data, we considered a classical analysis and Bayesian analysis assuming no informative priors for the parameters of the model with a cure fraction. A Bayesian approach was considered by using Markov Chain Monte Carlo Methods with Metropolis-Hasting algorithms steps to obtain the posterior summaries of interest. Some influence methods, such as the local influence, total local influence of an individual, local influence on predictions and generalized leverage were derived, analyzed and discussed in survival data with a cure fraction and covariates. The relevance of the approach was illustrated with a real data set, where it is shown that, by removing the most influential observations, the decision about which model best fits the data is changed.
LA - eng
KW - cure fraction; Bayesian inference; local influence; generalized leverage; survival data
UR - http://eudml.org/doc/42044
ER -