Why is Fisher's z transform numerically problematic near sample correlation ±1?
StatisticsLevel: AdvancedDependence and ranking
Why is Fisher's z transform numerically problematic near sample correlation ±1?
Hints
- Write atanh(r) as a log ratio.
- Inspect 1−r and 1+r.
Answer
This answer is part of mentoring
Advanced questions come with a full breakdown and a mock interview with a working quant researcher. The first call is free.
Source and licence: SciPy — statistical estimators and hypothesis tests · BSD-3-Clause · answer: Quantoros editorial