Diebold-Mariano test statistic converges to a stable non-Gaussian limit under infinite-variance loss differentials, and subsampling yields valid inference without estimating long-run variance or tail index.
Stochastic Processes and their Applications , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Heavy Tails and Predictive Ability Testing
Diebold-Mariano test statistic converges to a stable non-Gaussian limit under infinite-variance loss differentials, and subsampling yields valid inference without estimating long-run variance or tail index.