For rank-correlation M-estimators with U-process objectives, estimation works at the sqrt(p/n) rate when p/n converges to zero, but normal approximation needs the much stronger condition log(n/p^2) p^{3/2}/n^{1/4} to converge to zero.
D., Jansson, M., and Newey, W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On rank estimators in increasing dimensions
For rank-correlation M-estimators with U-process objectives, estimation works at the sqrt(p/n) rate when p/n converges to zero, but normal approximation needs the much stronger condition log(n/p^2) p^{3/2}/n^{1/4} to converge to zero.