Online Program Home
My Program

Abstract Details

Activity Number: 187
Type: Contributed
Date/Time: Monday, August 1, 2016 : 10:30 AM to 12:20 PM
Sponsor: Business and Economic Statistics Section
Abstract #319498
Title: Time Series Models for Ocean Wave Data
Author(s): Ellis Shaffer* and Nalini Ravishanker and James James O'Donnell
Companies: University of Connecticut and University of Connecticut and University of Connecticut
Keywords: Time series ; Dynamic linear models ; Duration models ; Marine science

Extreme wave events are of interest in marine sciences for their relationship to meteorological and sea state predictors as well as the potential impact on the human environment (i.e. coastal erosion, flooding and structural damage). Recent advances in statistical computing and duration modeling offer an opportunity to model wave height in new ways. With regard to the height of waves, one may specify a binary time series of extreme and non-extreme waves of a particular threshold and define a dynamic linear model. Integrated Nested Laplace Approximation (INLA) methods may be used for Bayesian computing offering speed increases over Markov Chain Monte Carlo (MCMC). With regard to the duration between extreme wave events, one may adapt and generalize the family of auto-regressive conditional duration (ACD) models introduced by Engle and Russell. These techniques are applied to public data from the National Oceanic and Atmospheric Administration's National Data Buoy Center.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association