Advanced search

When do we need more data? : a primer on calculating the value of information for applied ecologists

(2015) METHODS IN ECOLOGY AND EVOLUTION. 6(10). p.1219-1228
Author
Organization
Abstract
Applied ecologists continually advocate further research, under the assumption that obtaining more information will lead to better decisions. Value of information (VoI) analysis can be used to quantify how additional information may improve management outcomes: despite its potential, this method is still underused in environmental decision-making. We provide a primer on how to calculate the VoI and assess whether reducing uncertainty will change a decision. Our aim is to facilitate the application of VoI by managers who are not familiar with decision-analytic principles and notation, by increasing the technical accessibility of the tool. Calculating the VoI requires explicit formulation of management objectives and actions. Uncertainty must be clearly structured and its effects on management outcomes evaluated. We present two measures of the VoI. The expected value of perfect information is a calculation of the expected improvement in management outcomes that would result from access to perfect knowledge. The expected value of sample information calculates the improvement in outcomes expected by collecting a given sample of new data. We guide readers through the calculation of VoI using two case studies: (i) testing for disease when managing a frog species and (ii) learning about demographic rates for the reintroduction of an endangered turtle. We illustrate the use of Bayesian updating to incorporate new information. The VoI depends on our current knowledge, the quality of the information collected and the expected outcomes of the available management actions. Collecting information can require significant investments of resources; VoI analysis assists managers in deciding whether these investments are justified.
Keywords
adaptive management, Bayesian pre-posterior analysis, chytridiomycosis, conservation, decision analysis, experimental management, monitoring, CHYTRIDIOMYCOSIS, MANAGEMENT, SURVIVAL

Citation

Please use this url to cite or link to this publication:

Chicago
Canessa, Stefano, Gurutzeta Guillera-Arroita, José J Lahoz-Monfort, Darren M Southwell, Doug P Armstrong, Iadine Chadès, Robert C Lacy, and Sarah J Converse. 2015. “When Do We Need More Data? : a Primer on Calculating the Value of Information for Applied Ecologists.” Methods in Ecology and Evolution 6 (10): 1219–1228.
APA
Canessa, S., Guillera-Arroita, G., Lahoz-Monfort, J. J., Southwell, D. M., Armstrong, D. P., Chadès, I., Lacy, R. C., et al. (2015). When do we need more data? : a primer on calculating the value of information for applied ecologists. METHODS IN ECOLOGY AND EVOLUTION, 6(10), 1219–1228.
Vancouver
1.
Canessa S, Guillera-Arroita G, Lahoz-Monfort JJ, Southwell DM, Armstrong DP, Chadès I, et al. When do we need more data? : a primer on calculating the value of information for applied ecologists. METHODS IN ECOLOGY AND EVOLUTION. 2015;6(10):1219–28.
MLA
Canessa, Stefano, Gurutzeta Guillera-Arroita, José J Lahoz-Monfort, et al. “When Do We Need More Data? : a Primer on Calculating the Value of Information for Applied Ecologists.” METHODS IN ECOLOGY AND EVOLUTION 6.10 (2015): 1219–1228. Print.
@article{8522214,
  abstract     = {Applied ecologists continually advocate further research, under the assumption that obtaining more information will lead to better decisions. Value of information (VoI) analysis can be used to quantify how additional information may improve management outcomes: despite its potential, this method is still underused in environmental decision-making. We provide a primer on how to calculate the VoI and assess whether reducing uncertainty will change a decision. Our aim is to facilitate the application of VoI by managers who are not familiar with decision-analytic principles and notation, by increasing the technical accessibility of the tool. Calculating the VoI requires explicit formulation of management objectives and actions. Uncertainty must be clearly structured and its effects on management outcomes evaluated. We present two measures of the VoI. The expected value of perfect information is a calculation of the expected improvement in management outcomes that would result from access to perfect knowledge. The expected value of sample information calculates the improvement in outcomes expected by collecting a given sample of new data. We guide readers through the calculation of VoI using two case studies: (i) testing for disease when managing a frog species and (ii) learning about demographic rates for the reintroduction of an endangered turtle. We illustrate the use of Bayesian updating to incorporate new information. The VoI depends on our current knowledge, the quality of the information collected and the expected outcomes of the available management actions. Collecting information can require significant investments of resources; VoI analysis assists managers in deciding whether these investments are justified.},
  author       = {Canessa, Stefano and Guillera-Arroita, Gurutzeta and Lahoz-Monfort, Jos{\'e} J and Southwell, Darren M and Armstrong, Doug P and Chad{\`e}s, Iadine and Lacy, Robert C and Converse, Sarah J},
  issn         = {2041-210X},
  journal      = {METHODS IN ECOLOGY AND EVOLUTION},
  keyword      = {adaptive management,Bayesian pre-posterior analysis,chytridiomycosis,conservation,decision analysis,experimental management,monitoring,CHYTRIDIOMYCOSIS,MANAGEMENT,SURVIVAL},
  language     = {eng},
  number       = {10},
  pages        = {1219--1228},
  title        = {When do we need more data? : a primer on calculating the value of information for applied ecologists},
  url          = {http://dx.doi.org/10.1111/2041-210x.12423},
  volume       = {6},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: