What question did this study set out to answer?

To develop model selection and model averaging frameworks for M-estimation that improve confidence interval coverage while reducing sensitivity to outliers and heavy-tailed errors.

October 1, 2018Statistics

Model averaging for M-estimation

View Full Paper

Ask AI

Bookmark

Authors

JDJiang DuBeijing University of Technology ZZZhongzhan ZhangBeijing University of Technology TXTianfa XieBeijing University of Technology

Discussion

Member takes

Implication

Methodological study demonstrates robust model averaging improves confidence interval coverage and mitigates heavy-tailed errors, suggesting enhanced reliability for outlier-prone data.

Key Points

To develop model selection and model averaging frameworks for M-estimation that improve confidence interval coverage while reducing sensitivity to outliers and heavy-tailed errors.
Formulated robust adaptations of the focused information criterion and a frequentist model average estimator under general conditions for M-estimation.
Analyzed the theoretical asymptotic properties of the proposed estimators.
Evaluated performance using extensive numerical simulation studies and validation on two real-world datasets.
Demonstrated that the robust model averaging estimator successfully improves parameter confidence interval coverage probability in the presence of heavy-tailed response errors.
Confirmed satisfactory estimation performance and enhanced stability across both synthetic simulations and practical benchmark applications.

Cite This Study

Du et al. (2018) studied this question.

synapsesocial.com/papers/6a9d76563ad19a20338b14ea https://doi.org/10.1080/02331888.2018.1527842

View Full Paper

Ask AI

Bookmark

Implication

Methodological study demonstrates robust model averaging improves confidence interval coverage and mitigates heavy-tailed errors, suggesting enhanced reliability for outlier-prone data.

Model averaging for M-estimation

Discussion

Member takes

Implication

Key Points

Cite This Study

Model averaging for M-estimation

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider