mixgb: Multiple Imputation Through 'XGBoost'
Multiple imputation using 'XGBoost', bootstrapping and predictive mean matching as described in Deng and Lumley (2021) <arXiv:2106.01574>. It is built under Fully Conditional Specification, where 'XGBoost' imputation models are built for each incomplete variable. It supports various types of variables and offers different settings regarding bootstrapping and predictive mean matching. Visual diagnostic functions are also provided for inspecting multiply imputed values for incomplete variables.
| Version: | 0.1.0 |
| Depends: | R (≥ 3.5.0) |
| Imports: | data.table, ggplot2, Matrix, mice, Rfast, rlang, scales, stats, tidyr, utils, xgboost |
| Suggests: | knitr, rmarkdown, RColorBrewer |
| Published: | 2022-06-07 |
| Author: | Yongshi Deng 
[aut, cre],
Thomas Lumley [ths] |
| Maintainer: | Yongshi Deng <yongshi.deng at auckland.ac.nz> |
| BugReports: | https://github.com/agnesdeng/mixgb/issues |
| License: | GPL (≥ 3) |
| URL: | https://github.com/agnesdeng/mixgb, https://agnesdeng.github.io/mixgb/ |
| NeedsCompilation: | no |
| Materials: | README |
| CRAN checks: | mixgb results |
Documentation:
| Reference manual: | mixgb.pdf |
| Vignettes: |
Imputing newdata with a saved mixgb imputer mixgb: Multiple Imputation Through XGBoost |
Downloads:
| Package source: | mixgb_0.1.0.tar.gz |
| Windows binaries: | r-devel: mixgb_0.1.0.zip, r-release: mixgb_0.1.0.zip, r-oldrel: mixgb_0.1.0.zip |
| macOS binaries: | r-release (arm64): mixgb_0.1.0.tgz, r-oldrel (arm64): mixgb_0.1.0.tgz, r-release (x86_64): mixgb_0.1.0.tgz, r-oldrel (x86_64): mixgb_0.1.0.tgz |
Linking:
Please use the canonical form https://CRAN.R-project.org/package=mixgb to link to this page.