English

Listwise Deletion in High Dimensions

Other Statistics 2021-07-20 v2 Methodology

Abstract

We consider the properties of listwise deletion when both nn and the number of variables grow large. We show that when (i) all data has some idiosyncratic missingness and (ii) the number of variables grows superlogarithmically in nn, then, for large nn, listwise deletion will drop all rows with probability 1. Using two canonical datasets from the study of comparative politics and international relations, we provide numerical illustration that these problems may emerge in real world settings. These results suggest, in practice, using listwise deletion may mean using few of the variables available to the researcher.

Keywords

Cite

@article{arxiv.2101.11470,
  title  = {Listwise Deletion in High Dimensions},
  author = {J. Sophia Wang and Peter M. Aronow},
  journal= {arXiv preprint arXiv:2101.11470},
  year   = {2021}
}
R2 v1 2026-06-23T22:35:22.394Z