Rebuttal of “Problems in the extreme value analysis”

This paper rebuts claims published in this journal [33] as well as elsewhere [31], [32] and [34]: (a) that improved methodologies for extreme value analysis (EVA) developed over the past 60 years are invalid; (b) that EVA methodologies should revert to the status quo ante 1939; and (c) that, consequently, all regulations and codes of practice for extreme winds should be reassessed. This paper rebuts these claims and shows current EVA methodologies to be valid. The paper also shows that uncertainty due to sampling error, viz. how well a single observed sample represents the random process sampled, dominates over the choice of methodology.

► Claims made in Structural Safety, 30, 405–419 are examined.
► A fundamental fallacy in these claims is revealed.
► Other assertions on which the claims are based are demonstrated to be false.
► The main claim: that all methods for extreme value analysis since 1939 are invalid; is comprehensively rebutted.
► It is shown that uncertainty due to sampling error dominates over the choice of methodology.