Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.
Missing values are a common problem for researchers to deal with. A range of approaches can be used for this—from ignoring them and analysing “complete data” to imputing them through a model involving the observed (non-missing) data. The review by Donders et al 1 introduces the subject by presenting how missing data arise, describing the choices available for dealing with missing data, …