Estimating Extreme Wave Surges in the Presence of Missing Data

TL;DR

This paper addresses the challenge of estimating extreme wave surges using block maxima methods when data have missing observations, proposing and comparing parametric models through simulations and real data analysis.

Contribution

It introduces and evaluates parametric procedures to correct bias caused by missing data in extreme wave surge analysis within a block maxima framework.

Findings

Parametric models improve estimation accuracy with missing data.

Simulation results demonstrate the effectiveness of proposed methods.

Application to Atlantic Canada data illustrates practical utility.

Abstract

The block maxima approach, which consists of dividing a series of observations into equal sized blocks to extract the block maxima, is commonly used for identifying and modelling extreme events using the generalized extreme value (GEV) distribution. In the analysis of coastal wave surge levels, the underlying data which generate the block maxima typically have missing observations. Consequently, the observed block maxima may not correspond to the true block maxima yielding biased estimates of the GEV distribution parameters. Various parametric modelling procedures are proposed to account for the presence of missing observations under a block maxima framework. The performance of these estimators is compared through an extensive simulation study and illustrated by an analysis of extreme wave surges in Atlantic Canada.