An Intuitive Curve-Fit Approach to Probability-Preserving Prediction of\n Extremes

2014/08/07 by Allan McRobie, McRobie, Allan · 1 citation
Environmental Science · #Hydrology and Drought Analysis

paper · pdf · doi:10.48550/arxiv.1408.1532

Abstract

A method is described for predicting extremes values beyond the span of\nhistorical data. The method - based on extending a curve fitted to a location-\nand scale-invariant variation of the double-logarithmic QQ-plot - is simple and\nintuitive, yet it preserves probability to a good approximation. The procedure\nis developed on the Generalised Pareto Distribution (GPD), but is applicable to\nthe upper order statistics of a wide class of distributions.\n

Cited by

• A Noninformative Bayes-like Approach to Probability-Preserving Prediction of Extremes

Related

• A Noninformative Bayes-like Approach to Probability-Preserving Prediction of Extremes
• Probability-Matching Predictors for Extreme Extremes
• Statistical Prediction of Peaks Over a Threshold
• Graphical Models for Extremes
• The full-tails gamma distribution applied to model extreme values