Dealing with missing data 论文

摘要

What is done with missing data? Does the missingness mechanism matter? Is it a good idea to just use the
\ndefault options in the major statistical packages? Even some highly trained statisticians do this, so can the
\nnon-statistician analysing their own data cope with some of the better techniques for handling missing
\ndata? This paper shows how the mean and standard deviation are affected by different methods of
\nimputation, given different missingness mechanisms. Better options than the standard default options are
\navailable in the major statistical software, offering the chance to 'do the right thing' to the statistical and
\nnon-statistical community alike.