Home > Research > Publications & Outputs > Linex and double-linex regression for parameter...

Research

Associated organisational unit

Electronic data

  • linex_REVISED_3

    Accepted author manuscript, 709 KB, PDF document

    Available under license: Other

Links

Text available via DOI:

Keywords

View graph of relations

Linex and double-linex regression for parameter estimation and forecasting

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Linex and double-linex regression for parameter estimation and forecasting. / Tsionas, Mike G.
In: Annals of Operations Research, Vol. 323, No. 1-2, 30.04.2023, p. 229-245.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Tsionas, MG 2023, 'Linex and double-linex regression for parameter estimation and forecasting', Annals of Operations Research, vol. 323, no. 1-2, pp. 229-245. https://doi.org/10.1007/s10479-022-05131-2

APA

Tsionas, M. G. (2023). Linex and double-linex regression for parameter estimation and forecasting. Annals of Operations Research, 323(1-2), 229-245. https://doi.org/10.1007/s10479-022-05131-2

Vancouver

Tsionas MG. Linex and double-linex regression for parameter estimation and forecasting. Annals of Operations Research. 2023 Apr 30;323(1-2):229-245. Epub 2022 Dec 22. doi: 10.1007/s10479-022-05131-2

Author

Tsionas, Mike G. / Linex and double-linex regression for parameter estimation and forecasting. In: Annals of Operations Research. 2023 ; Vol. 323, No. 1-2. pp. 229-245.

Bibtex

@article{c9cd1cb19e374f98b14efda5e38447cb,
title = "Linex and double-linex regression for parameter estimation and forecasting",
abstract = "The choice of an estimation method has received considerable attention in the Operations Research literature. In this paper we depart from the standard use of linex and double-linex loss functions which are widely used in parameter estimation and forecasting problems and we propose a non-standard use for them. Specifically, we propose to use the corresponding linex and double-linex error densities as models for the errors of a regression problem when more emphasis should be placed on over-estimation or under-estimation of errors. The new techniques are applied to synthetic as well real data concerning the role of management in production as well as to an application of forecasting volatility in intradaily data.",
keywords = "Management Science and Operations Research, General Decision Sciences, Decision analysis, Linex loss functions, Regression problems, Estimation bias, Forecasting",
author = "Tsionas, {Mike G.}",
year = "2023",
month = apr,
day = "30",
doi = "10.1007/s10479-022-05131-2",
language = "English",
volume = "323",
pages = "229--245",
journal = "Annals of Operations Research",
issn = "0254-5330",
publisher = "Springer",
number = "1-2",

}

RIS

TY - JOUR

T1 - Linex and double-linex regression for parameter estimation and forecasting

AU - Tsionas, Mike G.

PY - 2023/4/30

Y1 - 2023/4/30

N2 - The choice of an estimation method has received considerable attention in the Operations Research literature. In this paper we depart from the standard use of linex and double-linex loss functions which are widely used in parameter estimation and forecasting problems and we propose a non-standard use for them. Specifically, we propose to use the corresponding linex and double-linex error densities as models for the errors of a regression problem when more emphasis should be placed on over-estimation or under-estimation of errors. The new techniques are applied to synthetic as well real data concerning the role of management in production as well as to an application of forecasting volatility in intradaily data.

AB - The choice of an estimation method has received considerable attention in the Operations Research literature. In this paper we depart from the standard use of linex and double-linex loss functions which are widely used in parameter estimation and forecasting problems and we propose a non-standard use for them. Specifically, we propose to use the corresponding linex and double-linex error densities as models for the errors of a regression problem when more emphasis should be placed on over-estimation or under-estimation of errors. The new techniques are applied to synthetic as well real data concerning the role of management in production as well as to an application of forecasting volatility in intradaily data.

KW - Management Science and Operations Research

KW - General Decision Sciences

KW - Decision analysis

KW - Linex loss functions

KW - Regression problems

KW - Estimation bias

KW - Forecasting

U2 - 10.1007/s10479-022-05131-2

DO - 10.1007/s10479-022-05131-2

M3 - Journal article

VL - 323

SP - 229

EP - 245

JO - Annals of Operations Research

JF - Annals of Operations Research

SN - 0254-5330

IS - 1-2

ER -