Multiple Imputation for Missing Data : A Cautionary Tale

@inproceedings{Allison1999MultipleIF,
  title={Multiple Imputation for Missing Data : A Cautionary Tale},
  author={Paul D. Allison},
  year={1999}
}
Two algorithms for producing multiple imputations for missing data are evaluated with simulated data. Software using a propensity score classifier with the approximate Bayesian boostrap produces badly biased estimates of regression coefficients when data on predictor variables are missing at random or missing completely at random. On the other hand, a regression-based method employing the data augmentation algorithm produces estimates with 
Highly Influential
This paper has highly influenced 17 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
150 Citations
10 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 150 extracted citations

References

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

An Empirical Evaluation of the Predictive Mean Matching Method for Imputing Missing Values.

  • Landerman, R Lawrence, Kenneth C. Land, Carl F. Pieper
  • Sociological Methods & Research
  • 1997
Highly Influential
3 Excerpts

Multiple Imputation after 18+ Years (with discussion.

  • Rubin, B Donald
  • Journal of the American Statistical Association
  • 1996

The Analysis of Social Science Data with Missing Values.

  • Little, A RoderickJ., Donald B. Rubin
  • Sociological Methods and Research
  • 1989

Multiple Imputation for Nonresponse in Surveys

  • Rubin, B Donald
  • 1987

Multiple Imputation for Interval Estimation from Simple Random Samples with Ignorable Nonresponse.

  • Rubin, B Donald, Nathaniel Schenker
  • Journal of the American Statistical Association
  • 1986

Formalizing Subjective Notion about the Effect of Nonrespondents in Sample Surveys.

  • Rubin, B Donald
  • Journal of the American Statistical Association
  • 1977

Inference and Missing Data.

  • Rubin, B Donald
  • Biometrika
  • 1976

Similar Papers

Loading similar papers…