Fiche du document
31 mars 2024
- 2404.00864
Sujets proches
Statistical data Cases, clinical reports, statistics Measures Statistical data Statistical analysis Statistical methods Statistical science Math Induction, Ampliative Ampliative induction Inference (Logic) Analysis (Mathematics) Economic theory Political economy Structures Edifices Halls Methods of analysis Analysis and chemistry Analytical methods Chemical analysis Analysis methods Analysis and examinationCiter ce document
Peter Reinhard Hansen et al., « Convolution-t Distributions », arXiv - économie
Partage / Export
Résumé
We introduce a new class of multivariate heavy-tailed distributions that are convolutions of heterogeneous multivariate t-distributions. Unlike commonly used heavy-tailed distributions, the multivariate convolution-t distributions embody cluster structures with flexible nonlinear dependencies and heterogeneous marginal distributions. Importantly, convolution-t distributions have simple density functions that facilitate estimation and likelihood-based inference. The characteristic features of convolution-t distributions are found to be important in an empirical analysis of realized volatility measures and help identify their underlying factor structure.