A note on reducing the bias of the approximate Bayesian bootstrap imputation variance estimator
Rubin & Schenker (1986) proposed the approximate Bayesian bootstrap, a two-stage resampling procedure, as a method of creating multiple imputations when missing data are ignorable. Kim (2002) showed that the multiple imputation variance estimator is biased for moderate sample sizes when this method is used. To reduce the bias, Kim (2002) proposed modifying the number of samples drawn at the first stage of the Bayesian bootstrap procedure. In this note, we suggest an alternative method for reducing the bias via a simple correction factor applied to the standard multiple imputation variance estimate. The proposed correction is more easily implemented and more efficient than the procedure proposed by Kim (2002). Copyright 2005, Oxford University Press.
Year of publication: |
2005
|
---|---|
Authors: | Parzen, Michael ; Lipsitz, Stuart R. ; Fitzmaurice, Garrett M. |
Published in: |
Biometrika. - Biometrika Trust, ISSN 0006-3444. - Vol. 92.2005, 4, p. 971-974
|
Publisher: |
Biometrika Trust |
Saved in:
Saved in favorites
Similar items by person
-
Approximate Median Regression via the Box-Cox Transformation
Fitzmaurice, Garrett M., (2007)
-
Lipsitz, Stuart R., (2009)
-
A Global Goodness-of-Fit Statistic for Cox Regression Models
Parzen, Michael, (1999)
- More ...