|
Abstract:
|
Extreme weather and climate events such as hot spells, snow storms, and floods have recently had a major impact on the economy, environment, and human well-being. However, when trying to develop a statistical model for climate data, a change-point is the single most important contributing factor for inaccurate or accurate results. Traditional change-point detection methods focus exclusively on detecting an alteration or a shift in the arithmetic mean. However, a change in the climate will first be recognized through changes in the frequency or intensity of extreme values. In this talk, we will first discuss our statistical method that uses extreme values to estimate the number and location of change-points within a climatic time series. Implementation of our Extreme value to various time series are discussed. We then compare the performance of our Extreme value method with a standard Bayesian method. Both methods are applied to simulated and real climate data.
|
