Rights statement: This is the peer reviewed version of the following article: Eastoe EF. Nonstationarity in peaks‐over‐threshold river flows: A regional random effects model. Environmetrics. 2019;e2560. https://doi.org/10.1002/env.2560 which has been published in final form at https://onlinelibrary.wiley.com/doi/full/10.1002/env.2560 This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.
Accepted author manuscript, 590 KB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Non-stationarity in peaks-over-threshold river flows
T2 - a regional random effects model
AU - Eastoe, Emma Frances
N1 - This is the peer reviewed version of the following article: Eastoe EF. Nonstationarity in peaks‐over‐threshold river flows: A regional random effects model. Environmetrics. 2019;e2560. https://doi.org/10.1002/env.2560 which has been published in final form at https://onlinelibrary.wiley.com/doi/full/10.1002/env.2560 This article may be used for non-commercial purposes in accordance With Wiley Terms and Conditions for self-archiving.2543
PY - 2019/8/1
Y1 - 2019/8/1
N2 - Under the influence of local- and large-scale climatological processes, extreme river flow events often show long-term trends, seasonality, inter-year variability and other characteristics of temporal non-stationarity. Properly accounting for this non-stationarity is vital for making accurate predictions of future floods. In this paper, a regional model based on the generalised Pareto distribution is developed for peaks-over-threshold river flow data sets when the event sizes are non-stationary. If observations are non-stationary and covariates are available then extreme value (semi-)parametric regression models may be used. Unfortunately the necessary covariates are rarely observed and, ifthey are, it is often not clear which process, or combination of processes, to include in the model. Within the statistical literature, latent process (or random effects) models are often used in such scenarios. We develop a regional time-varying random effects model which allows identificationof temporal non-stationarity in event sizes by pooling information across all sites in a spatially homogeneous region. The proposed model, which is an instance of a Bayesian hierarchical model, can be used to predict both unconditional extreme events such as the m-year maximum, as well as extreme events that condition on being in a given year. The estimated random effects may also tell us about likely candidates for the climatological processes which cause non-stationarity in the flood process. The model is applied to UK flood data from 817 stations spread across 81 hydrometric regions.
AB - Under the influence of local- and large-scale climatological processes, extreme river flow events often show long-term trends, seasonality, inter-year variability and other characteristics of temporal non-stationarity. Properly accounting for this non-stationarity is vital for making accurate predictions of future floods. In this paper, a regional model based on the generalised Pareto distribution is developed for peaks-over-threshold river flow data sets when the event sizes are non-stationary. If observations are non-stationary and covariates are available then extreme value (semi-)parametric regression models may be used. Unfortunately the necessary covariates are rarely observed and, ifthey are, it is often not clear which process, or combination of processes, to include in the model. Within the statistical literature, latent process (or random effects) models are often used in such scenarios. We develop a regional time-varying random effects model which allows identificationof temporal non-stationarity in event sizes by pooling information across all sites in a spatially homogeneous region. The proposed model, which is an instance of a Bayesian hierarchical model, can be used to predict both unconditional extreme events such as the m-year maximum, as well as extreme events that condition on being in a given year. The estimated random effects may also tell us about likely candidates for the climatological processes which cause non-stationarity in the flood process. The model is applied to UK flood data from 817 stations spread across 81 hydrometric regions.
U2 - 10.1002/env.2560
DO - 10.1002/env.2560
M3 - Journal article
VL - 30
JO - Environmetrics
JF - Environmetrics
SN - 1180-4009
IS - 5
M1 - e2560
ER -