Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Asymptotic Independence ex machina - Extreme Value Theory for the Diagonal Stochastic Recurrence Equation

Abstract : We consider multivariate stationary processes $(\boldsymbol{X}_t)$ satisfying a stochastic recurrence equation of the form $$ \boldsymbol{X}_t= \boldsymbol{m}M_t \boldsymbol{X}_{t-1} + \boldsymbol{Q}_t,$$ where $(M_t)$ and $(\boldsymbol{Q}_t)$ are iid random variables and random vectors, respectively, and $\boldsymbol{m}=\mathrm{diag}(m_1, \dots, m_d)$ is a deterministic diagonal matrix. We obtain a full characterization of the multivariate regular variation properties of $(\boldsymbol{X}_t)$, proving that coordinates $X_{t,i}$ and $X_{t,j}$ are asymptotically independent if and only if $m_i \neq m_j$; even though all coordinates rely on the same random input $(M_t)$. We describe extremal properties of $(\boldsymbol{X}_t)$ in the framework of vector scaling regular variation. Our results are applied to multivariate autoregressive conditional heteroskedasticity (ARCH) processes.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02591409
Contributor : Olivier Wintenberger <>
Submitted on : Friday, May 15, 2020 - 3:11:30 PM
Last modification on : Monday, May 18, 2020 - 9:26:23 AM

Files

2020_04_15_OlivierSebastian.pd...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02591409, version 1
  • ARXIV : 1907.10379

Citation

Sebastian Mentemeier, Olivier Wintenberger. Asymptotic Independence ex machina - Extreme Value Theory for the Diagonal Stochastic Recurrence Equation. 2020. ⟨hal-02591409⟩

Share

Metrics

Record views

9

Files downloads

10