Version française |   

Advantages and drawbacks of methods for estimating missing data
13-03-2018 | STATEC


The present study examines advantages and drawbacks of commonly used automatic variable selection methods for estimating missing data. A Monte Carlo simulation study on the basis of Luxembourgish EU-SILC data shows that automatic variable selection improves imputations. The results of the simulation study lead to the introduction of an imputation strategy, which incorporates advantages and limitations of automatic variable selection.