Open Access
Translator Disclaimer
2014 On inference of statistical regression models for extreme events based on incomplete observation data
Olga Kaiser, Illia Horenko
Commun. Appl. Math. Comput. Sci. 9(1): 143-174 (2014). DOI: 10.2140/camcos.2014.9.143

Abstract

We present a computationally efficient, semiparametric, nonstationary framework for statistical regression analysis of extremes with systematically missing covariates based on the generalized extreme value (GEV) distribution. It is shown that the involved regression model becomes nonstationary if some of the relevant model covariates are systematically missing. The resulting nonstationarity and the ill-posedness of the inverse problem are resolved by deploying the recently introduced finite-element time-series analysis methodology with bounded variation of model parameters (FEM-BV). The proposed FEM-BV-GEV approach allows a well-posed problem formulation and goes beyond probabilistic a priori assumptions of methods for analysis of extremes based on, e.g., nonstationary Bayesian mixture models, smoothing kernel methods or neural networks. FEM-BV-GEV determines the significant resolved covariates, reveals directly their influence on the trend behavior in probabilities of extremes and reflects the implicit impact of missing covariates. We compare the FEM-BV-GEV approach to the state-of-the-art GEV-CDN methodology (based on artificial neural networks) on test cases and real data according to four criteria: (1) information content of the models, (2) robustness with respect to the systematically missing information, (3) computational complexity and (4) interpretability of the models.

Citation

Download Citation

Olga Kaiser. Illia Horenko. "On inference of statistical regression models for extreme events based on incomplete observation data." Commun. Appl. Math. Comput. Sci. 9 (1) 143 - 174, 2014. https://doi.org/10.2140/camcos.2014.9.143

Information

Received: 20 May 2013; Revised: 28 November 2013; Accepted: 31 March 2014; Published: 2014
First available in Project Euclid: 20 December 2017

zbMATH: 1328.62209
MathSciNet: MR3212869
Digital Object Identifier: 10.2140/camcos.2014.9.143

Subjects:
Primary: 62G05 , 62G32 , 65R32
Secondary: 62F03 , 65C50

Keywords: finite-element method , generalized extreme-value distribution , nonparametric statistics , nonstationary time-series analysis , systematically missing information

Rights: Copyright © 2014 Mathematical Sciences Publishers

JOURNAL ARTICLE
32 PAGES


SHARE
Vol.9 • No. 1 • 2014
MSP
Back to Top