The article proposes a number of indices, taking values between zero and one, intended to measure data robustness of the inference on the given data set. These indices are based on repeated inference on the deleted samples and in some cases bootstrap samples, and thus are computer intensive.
All Science Journal Classification (ASJC) codes
- Statistics and Probability
- Statistics, Probability and Uncertainty
- Concepts of distance
- Confidence intervals
- Data robustness