Holli Capps Herron

Portfolio submission description

Investigation of Extreme Daily Precipitation at Axim, Ghana, Africa using Extreme Value Theory. The Axim meteorological station is from January 1961 to December 2012, and the daily precipitation in millimeters. The histogram (Figure 5) is right skewed where the highest frequency is low daily precipitation values. However, being interested in extreme daily rainfalls, this means the focus is on the right-tail, where there are very few observations. So standard statistics and the Central Limit Theorem do not work here. Instead, this is where Extreme Value Theory and Fisher-Tippett Theorem come in (Coles, 2001). “Extreme value theory is unique as a statistical discipline in that it develops techniques and models for describing the unusual rather than the usual… , extreme values are scarce, meaning that estimates are often required for levels of a process that are much greater than have already been observed. This implies an extrapolation from observed levels to unobserved levels, and extreme value theory provides a class of models to enable such extrapolation (Coles, 2001).” Three common methods for working with hydro-climatological extremes are the 1) Block maxima approach (BM), 2) the Peak Over Threshold (POT) approach, and 3) Point Process (PP) approach (Coles, 2001b, 2001c and 2001e). All three will be utilized and compared in this work, as each method has its own pros and cons.