Robustness of the linear mixed model to misspecified error distribution

  title={Robustness of the linear mixed model to misspecified error distribution},
  author={H{\'e}l{\`e}ne Jacqmin-Gadda and Solenne Sibillot and C{\'e}cile Proust-Lima and Jean-Michel Molina and Rodolphe Thi{\'e}baut},
  journal={Computational Statistics & Data Analysis},
A simulation study is performed to investigate the robustness of the maximum likelihood estimator of fixed effects from a linear mixed model when the error distribution is misspecified. Inference for the fixed effects under the assumption of independent normally distributed errors with constant variance is shown to be robust when the errors are either non-gaussian or heteroscedastic, except when the error variance depends on a covariate included in the model with interaction with time… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 48 extracted citations


Publications referenced by this paper.
Showing 1-10 of 25 references

Tables, Trends and Shapes

  • H. Jacqmin-Gadda, C. Fabrigoule, D. Commenges, J. F. Dartigues
  • 1997
Highly Influential
9 Excerpts

survival and CD4 counts in patients with AIDS

  • G. Verbeke, E. Lesaffre
  • J. Amer. Statist. Assoc
  • 1997
Highly Influential
5 Excerpts

Summarizing shape numerically : the gandh distribution

  • D. C. Hoaglin
  • 1985
Highly Influential
1 Excerpt

Model robust confidence intervals using maximum likelihood estimators

  • H. Jacqmin-Gadda
  • Data Analysis
  • 2007

Similar Papers

Loading similar papers…