Minimizing the cost of environmental management decisions by optimizing statistical thresholds

Scott A. Field, Andrew J. Tyre, Niclas Jonzén, Jonathan R. Rhodes, Hugh P. Possingham

Research output: Contribution to journalArticle

147 Citations (Scopus)

Abstract

Environmental management decisions are prone to expensive mistakes if they are triggered by hypothesis tests using the conventional Type I error rate (α) of 0.05. We derive optimal α-levels for decision-making by minimizing a cost function that specifies the overall cost of monitoring and management. When managing an economically valuable koala population, it shows that a decision based on α = 0.05 carries an expected cost over $5 million greater than the optimal decision. For a species of such value, there is never any benefit in guarding against the spurious detection of declines and therefore management should proceed directly to recovery action. This result holds in most circumstances where the species' value substantially exceeds its recovery costs. For species of lower economic value, we show that the conventional α-level of 0.05 rarely approximates the optimal decision-making threshold. This analysis supports calls for reversing the statistical 'burden of proof in environmental decision-making when the cost of Type II errors is relatively high.

Original languageEnglish (US)
Pages (from-to)669-675
Number of pages7
JournalEcology Letters
Volume7
Issue number8
DOIs
StatePublished - Aug 1 2004

Fingerprint

environmental management
decision making
cost
economic valuation
monitoring
decision
testing
economics

Keywords

  • Koala
  • Management
  • Optimal monitoring
  • Statistical power
  • Statistical significance
  • Type I error
  • Type II error

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics

Cite this

Minimizing the cost of environmental management decisions by optimizing statistical thresholds. / Field, Scott A.; Tyre, Andrew J.; Jonzén, Niclas; Rhodes, Jonathan R.; Possingham, Hugh P.

In: Ecology Letters, Vol. 7, No. 8, 01.08.2004, p. 669-675.

Research output: Contribution to journalArticle

Field, Scott A. ; Tyre, Andrew J. ; Jonzén, Niclas ; Rhodes, Jonathan R. ; Possingham, Hugh P. / Minimizing the cost of environmental management decisions by optimizing statistical thresholds. In: Ecology Letters. 2004 ; Vol. 7, No. 8. pp. 669-675.
@article{d4f2898c957e4fc0a08e9a67b3736dfb,
title = "Minimizing the cost of environmental management decisions by optimizing statistical thresholds",
abstract = "Environmental management decisions are prone to expensive mistakes if they are triggered by hypothesis tests using the conventional Type I error rate (α) of 0.05. We derive optimal α-levels for decision-making by minimizing a cost function that specifies the overall cost of monitoring and management. When managing an economically valuable koala population, it shows that a decision based on α = 0.05 carries an expected cost over $5 million greater than the optimal decision. For a species of such value, there is never any benefit in guarding against the spurious detection of declines and therefore management should proceed directly to recovery action. This result holds in most circumstances where the species' value substantially exceeds its recovery costs. For species of lower economic value, we show that the conventional α-level of 0.05 rarely approximates the optimal decision-making threshold. This analysis supports calls for reversing the statistical 'burden of proof in environmental decision-making when the cost of Type II errors is relatively high.",
keywords = "Koala, Management, Optimal monitoring, Statistical power, Statistical significance, Type I error, Type II error",
author = "Field, {Scott A.} and Tyre, {Andrew J.} and Niclas Jonz{\'e}n and Rhodes, {Jonathan R.} and Possingham, {Hugh P.}",
year = "2004",
month = "8",
day = "1",
doi = "10.1111/j.1461-0248.2004.00625.x",
language = "English (US)",
volume = "7",
pages = "669--675",
journal = "Ecology Letters",
issn = "1461-023X",
publisher = "Wiley-Blackwell",
number = "8",

}

TY - JOUR

T1 - Minimizing the cost of environmental management decisions by optimizing statistical thresholds

AU - Field, Scott A.

AU - Tyre, Andrew J.

AU - Jonzén, Niclas

AU - Rhodes, Jonathan R.

AU - Possingham, Hugh P.

PY - 2004/8/1

Y1 - 2004/8/1

N2 - Environmental management decisions are prone to expensive mistakes if they are triggered by hypothesis tests using the conventional Type I error rate (α) of 0.05. We derive optimal α-levels for decision-making by minimizing a cost function that specifies the overall cost of monitoring and management. When managing an economically valuable koala population, it shows that a decision based on α = 0.05 carries an expected cost over $5 million greater than the optimal decision. For a species of such value, there is never any benefit in guarding against the spurious detection of declines and therefore management should proceed directly to recovery action. This result holds in most circumstances where the species' value substantially exceeds its recovery costs. For species of lower economic value, we show that the conventional α-level of 0.05 rarely approximates the optimal decision-making threshold. This analysis supports calls for reversing the statistical 'burden of proof in environmental decision-making when the cost of Type II errors is relatively high.

AB - Environmental management decisions are prone to expensive mistakes if they are triggered by hypothesis tests using the conventional Type I error rate (α) of 0.05. We derive optimal α-levels for decision-making by minimizing a cost function that specifies the overall cost of monitoring and management. When managing an economically valuable koala population, it shows that a decision based on α = 0.05 carries an expected cost over $5 million greater than the optimal decision. For a species of such value, there is never any benefit in guarding against the spurious detection of declines and therefore management should proceed directly to recovery action. This result holds in most circumstances where the species' value substantially exceeds its recovery costs. For species of lower economic value, we show that the conventional α-level of 0.05 rarely approximates the optimal decision-making threshold. This analysis supports calls for reversing the statistical 'burden of proof in environmental decision-making when the cost of Type II errors is relatively high.

KW - Koala

KW - Management

KW - Optimal monitoring

KW - Statistical power

KW - Statistical significance

KW - Type I error

KW - Type II error

UR - http://www.scopus.com/inward/record.url?scp=3843062246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=3843062246&partnerID=8YFLogxK

U2 - 10.1111/j.1461-0248.2004.00625.x

DO - 10.1111/j.1461-0248.2004.00625.x

M3 - Article

AN - SCOPUS:3843062246

VL - 7

SP - 669

EP - 675

JO - Ecology Letters

JF - Ecology Letters

SN - 1461-023X

IS - 8

ER -