The use of mixtures for dealing with non-normal regression errors

@article{Bartolucci2005TheUO,
  title={The use of mixtures for dealing with non-normal regression errors},
  author={Francesco Bartolucci and Luisa Scaccia},
  journal={Computational Statistics & Data Analysis},
  year={2005},
  volume={48},
  pages={821-834}
}
In many situations, the distribution of the error terms of a linear regression model departs signi4cantly from normality. It is shown, through a simulation study, that an e5ective strategy to deal with these situations is 4tting a regression model based on the assumption that the error terms follow a mixture of normal distributions. The main advantage, with respect to the usual approach based on the least-squares method is a greater precision of the parameter estimates and con4dence intervals… CONTINUE READING