Plotting positions in extreme value analysis

Lasse Makkonen (Corresponding Author)

Research output: Contribution to journalArticleScientificpeer-review

67 Citations (Scopus)

Abstract

Plotting order-ranked data is a standard technique that is used in estimating the probability of extreme weather events. Typically, observations, say, annual extremes of a period of N years, are ranked in order of magnitude and plotted on probability paper. Some statistical model is then fitted to the order-ranked data by which the return periods of specific extreme events are estimated. A key question in this method is as follows: What is the cumulative probability P that should be associated with the sample of rank m? This issue of the so-called plotting positions has been debated for almost a century, and a number of plotting rules and computational methods have been proposed. Here, it is shown that in estimating the return periods there is only one correct plotting position: P = m/(N + 1). This formula predicts much shorter return periods of extreme events than the other commonly used methods. Thus, many estimates of the weather-related risks should be reevaluated and the related building codes and other related regulations updated.
Original languageEnglish
Pages (from-to)334-340
Number of pages7
JournalJournal of Applied Meteorology and Climatology
Volume45
Issue number2
DOIs
Publication statusPublished - 2006
MoE publication typeA1 Journal article-refereed

Fingerprint

return period
extreme event
weather
method
analysis

Keywords

  • extreme value analysis
  • plotting positions
  • return period
  • risk analysis
  • extreme events

Cite this

@article{1afd6f1d9cb440b2935863fe66f67fbb,
title = "Plotting positions in extreme value analysis",
abstract = "Plotting order-ranked data is a standard technique that is used in estimating the probability of extreme weather events. Typically, observations, say, annual extremes of a period of N years, are ranked in order of magnitude and plotted on probability paper. Some statistical model is then fitted to the order-ranked data by which the return periods of specific extreme events are estimated. A key question in this method is as follows: What is the cumulative probability P that should be associated with the sample of rank m? This issue of the so-called plotting positions has been debated for almost a century, and a number of plotting rules and computational methods have been proposed. Here, it is shown that in estimating the return periods there is only one correct plotting position: P = m/(N + 1). This formula predicts much shorter return periods of extreme events than the other commonly used methods. Thus, many estimates of the weather-related risks should be reevaluated and the related building codes and other related regulations updated.",
keywords = "extreme value analysis, plotting positions, return period, risk analysis, extreme events",
author = "Lasse Makkonen",
note = "Project code: R3SU00651",
year = "2006",
doi = "10.1175/JAM2349.1",
language = "English",
volume = "45",
pages = "334--340",
journal = "Journal of Applied Meteorology and Climatology",
issn = "1558-8424",
publisher = "American Meteorological Society",
number = "2",

}

Plotting positions in extreme value analysis. / Makkonen, Lasse (Corresponding Author).

In: Journal of Applied Meteorology and Climatology, Vol. 45, No. 2, 2006, p. 334-340.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Plotting positions in extreme value analysis

AU - Makkonen, Lasse

N1 - Project code: R3SU00651

PY - 2006

Y1 - 2006

N2 - Plotting order-ranked data is a standard technique that is used in estimating the probability of extreme weather events. Typically, observations, say, annual extremes of a period of N years, are ranked in order of magnitude and plotted on probability paper. Some statistical model is then fitted to the order-ranked data by which the return periods of specific extreme events are estimated. A key question in this method is as follows: What is the cumulative probability P that should be associated with the sample of rank m? This issue of the so-called plotting positions has been debated for almost a century, and a number of plotting rules and computational methods have been proposed. Here, it is shown that in estimating the return periods there is only one correct plotting position: P = m/(N + 1). This formula predicts much shorter return periods of extreme events than the other commonly used methods. Thus, many estimates of the weather-related risks should be reevaluated and the related building codes and other related regulations updated.

AB - Plotting order-ranked data is a standard technique that is used in estimating the probability of extreme weather events. Typically, observations, say, annual extremes of a period of N years, are ranked in order of magnitude and plotted on probability paper. Some statistical model is then fitted to the order-ranked data by which the return periods of specific extreme events are estimated. A key question in this method is as follows: What is the cumulative probability P that should be associated with the sample of rank m? This issue of the so-called plotting positions has been debated for almost a century, and a number of plotting rules and computational methods have been proposed. Here, it is shown that in estimating the return periods there is only one correct plotting position: P = m/(N + 1). This formula predicts much shorter return periods of extreme events than the other commonly used methods. Thus, many estimates of the weather-related risks should be reevaluated and the related building codes and other related regulations updated.

KW - extreme value analysis

KW - plotting positions

KW - return period

KW - risk analysis

KW - extreme events

U2 - 10.1175/JAM2349.1

DO - 10.1175/JAM2349.1

M3 - Article

VL - 45

SP - 334

EP - 340

JO - Journal of Applied Meteorology and Climatology

JF - Journal of Applied Meteorology and Climatology

SN - 1558-8424

IS - 2

ER -