Accounting for threshold uncertainty in extreme value estimation

By Andrea Tancredi, C. Anderson, Anthony OʼHagan. 2006

146 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/4dad81f2518adb4680f6d8e35e3b8571c3641b5b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Finance

In Statistics and Probability

Citations in the corpus

Threshold detection for the generalized Pareto distribution: Review of representative methods and application to the NOAA NCDC daily rainfall database (2016, background): “…affects the validity of the obtained estimates [see e.g., Rosbjerg and Madsen, 1992; Lang et al., 1999; Coles, 2001; Deidda and Puliga, 2006; Tancredi et al., 2006; Deidda, 2010; Chavez-Demoulin and Davison, 2012; Scarrott and MacDonald, 2012] and cannot be easily tackled through standard…”
INLA goes extreme: Bayesian tail regression for the estimation of high spatio-temporal quantiles (2018, background): “…also giving more ﬂexibility for balancing bias and variance; however, choosing a good threshold remains challenging (Frigessi et al. , 2002; Scarrott and MacDonald, 2012), which has lead some authors to implement Bayesian algorithms accounting for threshold uncertainty (Tancredi et al. , 2006).”
Extended generalised Pareto models for tail estimation (2011, methodology): “Tancredi et al. (2006) take into account the threshold uncertainty by allowing the threshold to be estimated as a statistical parameter in a mixture model.”
Bayesian analysis of extreme events with threshold estimation (2004, background): “Tancredi et al. (2002) tackles the threshold problem in a similar but independent way.”
Likelihood‐based procedures for threshold diagnostics and uncertainty in extreme value modelling (2012, methodology): “To illustrate the difficulties that are inherent in threshold selection, consider the data set of 154 flow rates exceeding 65 m3s−1 from the River Nidd, which was studied previously in Hosking and Wallis (1987), Davison and Smith (1990) and Tancredi et al. (2006).”