Regularized estimation of high‐dimensional vector autoregressions with weakly dependent innovations

Autor:	Marcelo C. Medeiros, Ricardo Masini, Eduardo F. Mendes
Rok vydání:	2021
Předmět:	Statistics and Probability Heteroscedasticity Current (mathematics) Series (mathematics) Applied Mathematics Gaussian Context (language use) symbols.namesake Lasso (statistics) Mixing (mathematics) symbols Applied mathematics Statistics Probability and Uncertainty Conditional variance Mathematics
Zdroj:	Journal of Time Series Analysis. 43:532-557
ISSN:	1467-9892 0143-9782
DOI:	10.1111/jtsa.12627
Popis:	There has been considerable advance in understanding the properties of sparse regularization procedures in high-dimensional models. In time series context, it is mostly restricted to Gaussian autoregressions or mixing sequences. We study oracle properties of LASSO estimation of weakly sparse vector-autoregressive models with heavy tailed, weakly dependent innovations with virtually no assumption on the conditional heteroskedasticity. In contrast to current literature, our innovation process satisfy an $L^1$ mixingale type condition on the centered conditional covariance matrices. This condition covers $L^1$-NED sequences and strong ($\alpha$-) mixing sequences as particular examples.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::d51057f08d0da485ab8daf2b0b023206 https://doi.org/10.1111/jtsa.12627 Zobrazit plný text záznamu