Biological Invasions

, Volume 8, Issue 8, pp 1595–1604 | Cite as

Quantifying uncertainty in predictions of invasiveness, with emphasis on weed risk assessment

  • Peter Caley
  • W. M. Lonsdale
  • P. C. Pheloung


Using the Australian Weed Risk Assessment (WRA) model as an example, we applied a combination of bootstrapping and Bayesian techniques as a means of explicitly estimating the posterior probability of weediness as a function of an import risk assessment model screening score. Our approach provides estimates of uncertainty around model predictions, after correcting for verification bias arising from the original training dataset having a higher proportion of weed species than would be the norm, and incorporates uncertainty in current knowledge of the prior (base-rate) probability of weediness. The results confirm the high sensitivity of the posterior probability of weediness to the base-rate probability of weediness of plants proposed for importation, and demonstrate how uncertainty in this base-rate probability manifests itself in uncertainty surrounding predicted probabilities of weediness. This quantitative estimate of the weediness probability posed by taxa classified using the WRA model, including estimates of uncertainty around this probability for a given WRA score, would enable bio-economic modelling to contribute to the decision process, should this avenue be pursued. Regardless of whether or not this avenue is explored, the explicit estimates of uncertainty around weed classifications will enable managers to make better informed decisions regarding risk. When viewed in terms of likelihood of weed introduction, the current WRA model outcomes of ‘accept’, ‘further evaluate’ or ‘reject’, whilst not always accurate in terms of weed classification, appear consistent with a high-expected cost of mistakenly introducing a weed. The methods presented have wider application to the quantitative prediction of invasive species for situations where the base-rate probability of invasiveness is subject to uncertainty, and the accuracy of the screening test imperfect.


Bayesian bootstrapping decision support invasion prediction modelling uncertainty risk assessment 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Begg, CB, Greenes, RA 1983Assessment of diagnostic tests when disease verification is subject to selection biasBiometrics39207215PubMedCrossRefGoogle Scholar
  2. Burnham, KP, Anderson, DR 2002Model Selection and Multimodel Inference: A Practical Information-Theoretic ApproachSpringer-VerlagNew YorkGoogle Scholar
  3. Daehler, CC, Carino, DA 2000Predicting invasive plants: prospects for a general screening system based on current regional modelsBiological Invasions293102CrossRefGoogle Scholar
  4. Daehler, CC, Denslow, JS, Ansari, S, Kuo, H-C 2004A risk-assessment system for screening out invasive pest plants from Hawaii and other Pacific islandsConservation Biology18360368CrossRefGoogle Scholar
  5. Duncan, RP, Williams, PA 2002aDarwin’s naturalization hypothesis challengedNature417608609CrossRefGoogle Scholar
  6. Duncan, RP, Williams, PA 2002bTaxonomic patterns in the naturalisation rate of plant species in New ZealandSpafford Jacob, HDodd, JMoore, JH eds. Thirteenth Australian Weeds ConferencePlant Protection Society of Western AustraliaPerth, Western Australia183185Google Scholar
  7. Efron, B, Tibshirani, RJ 1993An Introduction to the BootstrapChapman and HallNew YorkGoogle Scholar
  8. Ewel, JJ, O’Dowd, DJ, Bergelson, J, Daehler, CC, D’Antonio, CM, Gomez, LD, Gordon, DR, Hobbs, RJ, Holt, A, Hopper, KR, Hughes, CE, LaHart, M, Leakey, RRB, Lee, WG, Loope, LL, Lorence, DH, Louda, SM, Lugo, AE, McEvoy, PB, Richardson, DM, Vitousek, PM 1999Deliberate introductions of species: research needsBioScience49619630CrossRefGoogle Scholar
  9. Gigerenzer, G 2002Calculated Risks: How to Know When Numbers Deceive YouSimon and SchusterNew YorkGoogle Scholar
  10. Heger, T, Trepl, L 2003Predicting biological invasionsBiological Invasions5313321CrossRefGoogle Scholar
  11. Hughes, G, Madden, LV 2003Evaluating predictive models with application in regulatory policy for invasive weedsAgricultural Systems76755774CrossRefGoogle Scholar
  12. Kohavi, R 1995A study of cross-validation and bootstrap for accuracy estimation and model selectionMellish, CS eds. Proceedings of the Fourteenth International Joint Conference on Artificial IntelligenceMorgan Kaufmann Publishers, Inc.Montreal, Quebec11371143Google Scholar
  13. Kolar, CS, Lodge, DM 2001Progress in invasion biology: predicting invadersTrends in Ecology and Evolution16199204PubMedCrossRefGoogle Scholar
  14. Kolar, CS, Lodge, DM 2002Ecological predictions and risk assessment for alien fishes in North AmericaScience29812331236PubMedCrossRefGoogle Scholar
  15. Kuhnert, PM, Mengersen, K 2003Reliability measures for local nodes assessment in classification treesJournal of Computational and Graphical Studies12119CrossRefGoogle Scholar
  16. Lonsdale, WM 1994Inviting trouble: introduced pasture species in northern AustraliaAustralian Journal of Ecology19345354CrossRefGoogle Scholar
  17. Mack, RN, Simberloff, D, Lonsdale, WM, Evans, H, Clout, M, Bazzaz, FA 2000Biotic invasions: causes, epidemiology, global consequences, and controlEcological Applications10689710CrossRefGoogle Scholar
  18. Manel, S, Williams, HC, Ormerod, SJ 2001Evaluating presence–absence models in ecology: the need to account for prevalenceJournal of Applied Ecology38921931CrossRefGoogle Scholar
  19. Matthews, RAJ 1996Base-rate errors and rain forecastsNature382766CrossRefGoogle Scholar
  20. Matthews, RAJ 1997Decision-theoretic limits on earthquake predictionGeophysics Journal International131526529Google Scholar
  21. Metz, CE 1978Basic principles of ROC analysisSeminars in Nuclear Medicine8283298PubMedGoogle Scholar
  22. Pearce, J, Ferrier, S 2000Evaluating the predictive performance of habitat models developed using logistic regressionEcological Modelling133225245CrossRefGoogle Scholar
  23. Pheloung, PC, Williams, PA, Halloy, SR 1999A weed risk assessment model for use as a biosecurity tool evaluating plant introductionsJournal of Environmental Management57239251CrossRefGoogle Scholar
  24. Pimentel, DL, Lach, L, Zuniga, R, Morrison, D 2000Environmental and economic costs associated with non-indigenous species in the United StatesBioScience505365CrossRefGoogle Scholar
  25. Reichard, SH, Hamilton, CW 1997Predicting invasions of woody plants introduced into North AmericaConservation Biology11193203CrossRefGoogle Scholar
  26. Richardson, DM, Pysek, P, Rejmanek, M, Barbour, MG, Panetta, FD, West, CJ 2000Naturalization and invasion of alien plants: concepts and definitionsDiversity and Distributions693107CrossRefGoogle Scholar
  27. Ruesink, JL, Parker, IM, Groom, MJ, Kareiva, PM 1995Reducing the risks of nonindigenous species introductions: guilty until proven innocentBioScience45465477CrossRefGoogle Scholar
  28. Scott, JK, Panetta, FD 1993Predicting the Australian weed status of southern African plantsJournal of Biogeography208793CrossRefGoogle Scholar
  29. Smith C (1999) Studies on Weed Risk Assessment. Master of Applied Science, University of AdelaideGoogle Scholar
  30. Smith, CS, Lonsdale, WM, Fortune, J 1999When to ignore advice: invasion predictions and decision theoryBiological Invasions18996CrossRefGoogle Scholar
  31. United States National Research Council2002Predicting Invasions of Nonindigenous Plants and Plant PestsNational Academy PressWashington, D.CGoogle Scholar
  32. Vose, D 2000Risk Analysis: A Quantitative GuideJohn Wiley and SonsChichester, West SussexGoogle Scholar
  33. Williamson, M, Fitter, A 1996The varying success of invadersEcology7716611665CrossRefGoogle Scholar

Copyright information

© Springer 2006

Authors and Affiliations

  • Peter Caley
    • 1
    • 2
  • W. M. Lonsdale
    • 1
    • 2
  • P. C. Pheloung
    • 2
    • 3
  1. 1.CSIRO EntomologyCanberraAustralia
  2. 2.Cooperative Research Centre for Australia Weed ManagementGlen OsmondAustralia
  3. 3.Department of AgricultureFisheries and ForestryCanberraAustralia

Personalised recommendations