Multiple Imputation with Diagnostics (mi) in R: Opening Windows into the Black Box

By Yu-Sung Su, Andrew Gelman, Jennifer L. Hill, Masanao Yajima. 2011

667 citations recorded by the source corpus.

Our mi package in R has several features that allow the user to get inside the imputation process and evaluate the reasonableness of the resulting models and imputations. These features include: choice of predictors, models, and transformations for chained imputation models; standard and binned residual plots for checking the fit of the conditional distributions used for imputation; and plots for comparing the distributions of observed and imputed data. In addition, we use Bayesian models and weakly informative prior distributions to construct more stable estimates of imputation models. Our goal is to have a demonstration package that (a) avoids many of the practical problems that arise with existing multivariate imputation programs, and (b) demonstrates state-of-the-art diagnostics that can be applied more generally and can be incorporated into the software of others.

Subfields: Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/c34f900a88d451cae1cbe14061881f8a6cb99c3b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

A Survey on Multi-View Clustering (2017, neutral): “Simply replacing the missing entries with zero or mean values [153] is a common way to deal with the missing value problem, and multiple imputation [154] is also a popular method in statistical field.”
Imputation with the R Package VIM (2016, methodology): “Regarding the mix of variables, an exception is the package mi (Su, Gelman, Hill, and Yajima 2011) which uses a two-part model to deal with semi-continuous variables and which supports a mix of semi-continuous, continuous and categorical variables, further it allows for multiple imputation.”
MICE: Multivariate Imputation by Chained Equations in R (2011, background): “This methodology is attractive if the multivariate distribution is a reasonable description of the data.”
Multiple imputation for continuous variables using a Bayesian principal component analysis† (2014, methodology): “e Amelia (Honaker et al., 2011) and a second one based on chained equations implemented intheR-packagemice (van Buuren and Groothuis-Oudshoorn, 2011). Note that other packages such as the mi package (Su et al., 2011) can be used to perform multiple imputation using chained equations. • Amelia impute”
Predictive mean matching imputation of semicontinuous variables (2014, methodology): “New algorithms and packages with support for semicontinuous data have emerged, such as the R-packages mi (Su et al., 2011) and VIM (Templ, Kowarik and Filzmoser, 2011).”
BHPMF – a hierarchical Bayesian approach to gap-filling and trait prediction for macroecology and functional biogeography (2015, methodology): “multiple imputation (MI) (Rubin, 1987; Su et al., 2011) and multivariate imputation using chained equations (MICE) (Rubin, 1987; van Buuren & Groothuis-Oudshoorn, 2011), or/and spatial correlations within the trait matrix (e.”