Resamping variance estimation in surveys with missing data

We discuss variance estimation by resampling in surveys in which data are missing. We derive a formula for jackknife linearization in the case of calibrated estimation with deterministic regression imputation, and compare the resulting variance estimates with balanced repeated replication with and without grouping, the bootstrap, the block jackknife, and multiple imputation, for simulated data based on the Swiss Household Budget Survey. Jackknife linearisation, the bootstrap, and multiple imputation perform best in terms of relative bias and mean square error.