Why can iterative sigma clipping remove more points than one pass with the original mean and SD?
StatisticsLevel: IntermediateRobust summaries
Why can iterative sigma clipping remove more points than one pass with the original mean and SD?
Hints
- The reference distribution changes.
- Thresholds are recomputed.
Answer
Each removal changes the mean and SD, moving the cutoff. Previously retained points can then cross the recomputed threshold.
Source and licence: SciPy — statistical estimators and hypothesis tests · BSD-3-Clause · answer: Quantoros editorial