Bootstrap for Imputed Survey Data
Jun Shao, Randy R. Sitter · Journal of the American Statistical Association · 1996
Most surveys use imputation to compensate for missing data. However, treating the imputed data set as the complete data set and directly applying existing methods (e.g., the linearization, the jackknife, and the bootstrap) for variance estimation and/or statistical inference does not produce valid results, because these methods do not account for the effect of missing data and/or imputation. In this article we show that correct bootstrap estimates can be obtained by imitating the process of imputing the original data set in the bootstrap resampling; that is, by imputing the bootstrap data sets in exactly the same way that the original data set is imputed. The proposed bootstrap is asymptotically valid irrespective of the sampling design, the imputation method, or the type of statistic used in inference. This enables us to use a unified method in a variety of problems, and in fact this is the only method that works without any restriction on the sampling design, the imputation method, or the type of statistic.
Cited by 205 works. doi:10.1080/01621459.1996.10476997
Authors
References
- Bootstrap Methods: Another Look at the Jackknife
- Multiple Imputation for Nonresponse in Surveys
- Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy
- Multiple Imputation for Interval Estimation From Simple Random Samples With Ignorable Nonresponse
- Resampling Inference With Complex Survey Data
- Jackknife Variance Estimation with Survey Data Under Hot Deck Imputation
- Missing Data, Imputation, and the Bootstrap
- Asymptotic Results for Multiple Imputation
- A Resampling Procedure for Complex Survey Data
- Asymptotic Normality and the Bootstrap in Stratified Sampling