A note on the asymptotic distribution of LASSO estimator for correlated data

Autor:	Shuva Gupta
Rok vydání:	2012
Předmět:	Statistics and Probability Structure (category theory) Estimator Asymptotic distribution V-statistic Multivariate normal distribution Regression analysis Lasso (statistics) Statistics Statistics::Methodology Applied mathematics Statistics Probability and Uncertainty Special case Mathematics
Zdroj:	Sankhya A. 74:10-28
ISSN:	0976-8378 0976-836X
DOI:	10.1007/s13171-012-0006-8
Popis:	The asymptotic distribution of the Lasso estimator for regression models with independent errors has been investigated by Knight and Fu (2000). In this note we extend these results to regression models with a general weak dependence structure. We determine the asymptotic distribution of the Lasso estimator when the number of parameters M is fixed and the number of observations, n, converges to infinity. We show that, for an appropriate choice of the tuning parameter of the method, this asymptotic distribution reduces to a multivariate normal distribution. As an illustrative example, the special case of AR(1) is also investigated.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::57899ffd4e1a28f14852f1e19b9149b7 https://doi.org/10.1007/s13171-012-0006-8 Zobrazit plný text záznamu Full text from SpringerLink