miceMNAR-package: Missing not at Random Imputation Models for Multiple...

In miceMNAR: Missing not at Random Imputation Models for Multiple Imputation by Chained Equation

Description

Provides imputation models and functions for binary or continuous Missing Not At Random (MNAR) outcomes through the use of the 'mice' package. The mice.impute.hecknorm() function provides imputation model for continuous outcome based on Heckman's model also named sample selection model as described in Galimard et al (2018) and Galimard et al (2016) <doi:10.1002/sim.6902>. The mice.impute.heckprob() function provides imputation model for binary outcome based on bivariate probit model as described in Galimard et al (2018).

As these two previous imputation models require to specify a selection and an outcome equation, mice() function has to be adapted using MNARargument().

Details

Index: This package was not yet installed at build time.

Warning

This package is only validated for the imputation of MNAR outcome. However, it is implemented to impute several MNAR variables in the same process. Such implementation must be realised carefully.

Author(s)

Jacques-Emmanuel Galimard [aut, cre] (INSERM, U1153, ECSTRA team), Matthieu Resche-Rigon [aut] (INSERM, U1153, ECSTRA team)

Maintainer: Jacques-Emmanuel Galimard <[e-mail]>

References

Galimard, J.E., Chevret, S., Curis, E., and Resche-Rigon, M. (2018). Heckman imputation models for binary or continuous MNAR missing outcomes and MAR missing predictors. BMC Medical Research Methodology (In press). Galimard, J.-E., Chevret, S., Protopopescu, C., and Resche-Rigon, M. (2016) A multiple imputation approach for MNAR mechanisms compatible with Heckman's model. Statistics In Medicine, 35: 2907-2920. doi:10.1002/sim.6902.

See Also

mice copulaSampleSel SemiParBIV

selection

miceMNAR documentation built on May 2, 2019, 8:31 a.m.