Review Articles

Variable screening with missing covariates: a discussion of ‘statistical inference for nonignorable missing data problems: a selective review’ by Niansheng Tang and Yuanyuan Ju

Fang Fang ,

School of Statistics, East China Normal University

ffang@sfs.ecnu.edu.cn

Lyu Ni

School of Statistics, East China Normal University

Pages 134-136 | Received 20 Aug. 2018, Accepted 09 Sep. 2018, Published online: 22 Sep. 2018,
  • Abstract
  • Full Article
  • References
  • Citations

ABSTRACT

Feature screening with missing data is a critical problem but has not been well addressed in the literature. In this discussion we propose a new screening index based on “information value” and apply it to feature screening with missing covariates.

References

  1. Fan, J., & Lv, J. (2008). Sure independent screening for ultrahigh dimensional feature space (with discussion). Journal of Royal Statistical Society, Series B, 70, 849911. doi: 10.1111/j.1467-9868.2008.00674.x [Google Scholar]
  2. Fang, L., & Ni, F. (2016). Entropy-based model-free feature screening for ultrahigh-dimensional multiclass classification. Journal of Nonparametric Statistics, 28, 515530. doi: 10.1080/10485252.2016.1167206 [Taylor & Francis Online], [Google Scholar]
  3. Huang, D. Y., Li, R. Z., & Wang, H. S. (2014). Feature screening for ultrahigh dimensional categorical data with applications. Journal of Business & Economic Statistics, 32, 237244. doi: 10.1080/07350015.2013.863158 [Taylor & Francis Online], [Google Scholar]
  4. Lai, P., Liu, Y. M., Liu, Z., & Wan, Y. (2017). Model free feature screening for ultrahigh dimensional data with responses missing at random. Computational Statistics & Data Analysis, 105, 201216. doi: 10.1016/j.csda.2016.08.008 [Web of Science ®], [Google Scholar]
  5. Ni, L., Fang, F., & Wan, F. J. (2017). Adjusted pearson chi-square feature screening for multi-classification with ultrahigh dimensional data. Metrika, 80, 805828. doi: 10.1007/s00184-017-0629-9 [Google Scholar]
  6. Wang, Q. H., & Li, Y. J. (2018). How to make model-free feature screening approaches for full data applicable to the case of missing response?. Scandinavian Journal of Statistics, 45, 324346. doi: 10.1111/sjos.12290 [Google Scholar]