Optimal estimation of direction in regression models with large number of parameters

Gillard, Jonathan ORCID: https://orcid.org/0000-0001-9166-298X and Zhigljavsky, Anatoly ORCID: https://orcid.org/0000-0003-0630-8279 2018. Optimal estimation of direction in regression models with large number of parameters. Applied Mathematics and Computation 318 , pp. 281-289. 10.1016/j.amc.2017.05.050

Preview

PDF - Accepted Post-Print Version Download (340kB) | Preview

Abstract

We consider the problem of estimating the optimal direction in regression by maximizing the probability that the scalar product between the vector of unknown parameters and the chosen direction is positive. The estimator maximizing this probability is simple in form, and is especially useful for situations where the number of parameters is much larger than the number of observations. We provide examples which show that this estimator is superior to state-of-the-art methods such as the LASSO for estimating the optimal direction.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Mathematics
Subjects:	Q Science > QA Mathematics
Uncontrolled Keywords:	Random balance; Screening experiments; Box–Wilson methodology; LASSO; Ridge regression
Publisher:	Elsevier
ISSN:	0096-3003
Date of First Compliant Deposit:	1 June 2017
Date of Acceptance:	14 May 2017
Last Modified:	20 Nov 2024 09:45
URI:	https://orca.cardiff.ac.uk/id/eprint/101058

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item