Variable selection for multiply-imputed data with application to dioxin exposure study.

@article{Chen2013VariableSF,
  title={Variable selection for multiply-imputed data with application to dioxin exposure study.},
  author={Qixuan Chen and Sijian Wang},
  journal={Statistics in medicine},
  year={2013},
  volume={32 21},
  pages={3646-59}
}
Multiple imputation (MI) is a commonly used technique for handling missing data in large-scale medical and public health studies. However, variable selection on multiply-imputed data remains an important and longstanding statistical problem. If a variable selection method is applied to each imputed dataset separately, it may select different variables for different imputed datasets, which makes it difficult to interpret the final model or draw scientific conclusions. In this paper, we propose a… CONTINUE READING

Citations

Publications citing this paper.
Showing 1-10 of 20 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 34 references

Multiple imputation for nonresponse in surveys

D. B. Rubin
New York: Wiley. Rubin D.B. and Schenker, N • 1987
View 8 Excerpts
Highly Influenced

regression models with missing covariates

Y. Lin
Biometrics • 2006
View 5 Excerpts
Highly Influenced

Statistical analysis with missing data, 2nd edition

J. A. Little, D. B. Rubin
Wiley. • 2002
View 3 Excerpts
Highly Influenced

Nearly unbiased variable selection under minimax concave penalty

C. Zhang
Annals of Statistics 38, 894-942. • 2010
View 2 Excerpts

Similar Papers

Loading similar papers…