Separability of high-dimensional matrix covariances can be tested by Monte Carlo sphericity after separable MLE whitening, with an angular version robust to heavy-tailed elliptical laws and consistency under dense alternatives.
Journal of the American Statistical Association , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Testing Covariance Separability in High Dimensions
Separability of high-dimensional matrix covariances can be tested by Monte Carlo sphericity after separable MLE whitening, with an angular version robust to heavy-tailed elliptical laws and consistency under dense alternatives.