TY - JOUR

T1 - On a new extreme value distribution

T2 - characterization, parametric quantile regression, and application to extreme air pollution events

AU - Saulo, Helton

AU - Vila, Roberto

AU - Bittencourt, Verônica L.

AU - Leão, Jeremias

AU - Leiva, Víctor

AU - Christakos, George

N1 - Funding Information:
The present research was funded partially by (i) CNPq (grant number 309674/2020-4), Brazil (H. Saulo) and (ii) FONDECYT grant number 1200525 (V. Leiva and H. Saulo) from the National Agency for Research and Development (ANID) of the Chilean government under the Ministry of Science, Technology, Knowledge, and Innovation.
Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

PY - 2022

Y1 - 2022

N2 - Extreme-value distributions are important when modeling weather events, such as temperature and rainfall. These distributions are also important for modeling air pollution events. Particularly, the extreme-value Birnbaum-Saunders regression is a helpful tool in the modeling of extreme events. However, this model is implemented by adding covariates to the location parameter. Given the importance of quantile regression to estimate the effects of covariates along the wide spectrum of a response variable, we introduce a quantile extreme-value Birnbaum-Saunders distribution and its corresponding quantile regression model. We implement a likelihood-based approach for parameter estimation and consider two types of statistical residuals. A Monte Carlo simulation is performed to assess the behavior of the estimation method and the empirical distribution of the residuals. We illustrate the introduced methodology with unpublished real air pollution data.

AB - Extreme-value distributions are important when modeling weather events, such as temperature and rainfall. These distributions are also important for modeling air pollution events. Particularly, the extreme-value Birnbaum-Saunders regression is a helpful tool in the modeling of extreme events. However, this model is implemented by adding covariates to the location parameter. Given the importance of quantile regression to estimate the effects of covariates along the wide spectrum of a response variable, we introduce a quantile extreme-value Birnbaum-Saunders distribution and its corresponding quantile regression model. We implement a likelihood-based approach for parameter estimation and consider two types of statistical residuals. A Monte Carlo simulation is performed to assess the behavior of the estimation method and the empirical distribution of the residuals. We illustrate the introduced methodology with unpublished real air pollution data.

KW - Environmental data

KW - Extreme-value distributions

KW - Likelihood-based methods

KW - Monte Carlo simulation

KW - Quantile regression

KW - Residuals

KW - Shape analysis

UR - http://www.scopus.com/inward/record.url?scp=85141350539&partnerID=8YFLogxK

U2 - 10.1007/s00477-022-02318-8

DO - 10.1007/s00477-022-02318-8

M3 - Article

AN - SCOPUS:85141350539

JO - Stochastic Environmental Research and Risk Assessment

JF - Stochastic Environmental Research and Risk Assessment

SN - 1436-3240

ER -