Publication Options for measuring the distance between two distributions in practice

Dealing with incomplete data sets is an important aspect of data processing. It is often not known for what analysis a set of data from official statistics will later be used in science and research. Therefore, it is reasonable to reproduce the distribution of the original data as closely as possible. To this end, it is important to choose the most appropriate imputation method. The thesis described in this article uses a simulation study to assess the suitability of different quantities for comparing the goodness of fit of different imputation methods, based on two example data sets from official statistics.

Author: Maria Thurow

Article published in "WISTA – Scientific Journal", 2-2022