Abstract
The apparently simple problem of measuring classification accuracy is reviewed. Guidelines are suggested for the choice of appropriate measures of classification accuracy, including those that assess improvement over chance and the imposition of misclassification costs. Particular attention is paid to the selection of appropriate data for accuracy assessment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Augustin, N. H., Mugglestone, M. A. and Buckland, S. T. 1996. An autologistic model for the spatial distribution of wildlife. Journal of Applied Ecology, 33: 339–347.
Blayo, F., Chevenal, Y., Guérin-Dugué, A., Chentouf, R., Aviles-Cruz, G, Madrenas, J., Moreno, M. and Voz, J. L. 1995. Enhanced Learning for Evolutive Neural Architecture.
Deliverable R3-B4-P Task B4: Benchmarks. ESPIRIT Basic Research Project Number 6891. Available from ftp.dice.ucl.ac.be/pub/neural-nets/ELANA/databases
Bradley, A. P. 1997. The use of the area under the ROC curve in the estimation of machine learning algorithms. Pattern Recognition, 30: 1145–1159.
Brennan, L. A., Block, W. M. and Gutiérrez, R. J. 1986. The use of multivariate statistics for developing habitat suitability index models. In: Wildlife 2000: Modelling habitat relationships of terrestrial vertebrates, ed. J. A. Verner, M. L. Morrison and C. J. Ralph, pp. 177–182. University of Wisconsin Press, Madison.
Buckland, S. T. and Elston, D. A. 1993. Empirical models for the spatial distribution of wildlife. Journal of Applied Ecology, 30: 478–495.
Capen, D. E., Fenwick, J. W., Inkley, D. B. and Boynton, A. C. 1986. Multivariate models of songbird habitat in New England forests. In: Wildlife 2000: Modelling habitat relationships of terrestrial vertebrates, ed. J. A. Verner, M. L. Morrison and C. J. Ralph, pp. 171–175. University of Wisconsin Press, Madison.
Chatfield, C. 1995. Model uncertainty, data mining and statistical inference. Journal of the Royal Statistical Society, Series A, 158: 419–466.
Cohen, P. 1995. Empirical methods for artificial intelligence. MIT, Cambridge, MA.
Deleo, J. M. 1993. Receiver operating characteristic laboratory (ROCLAB): software for developing decision strategies that account for uncertainty, pp 318–325 in Proceedings of the Second International Symposium on Uncertainty Modelling and Analysis. IEEE, Computer Society Press, College Park, MD.
Deleo, J. M. and Campbell, G. 1990. The fuzzy receiver operating characteristic function and medical decisions with uncertainty. In: Proceedings of the First International Symposium on Uncertainty Modelling and Analysis. IEEE, Computer Society Press, College Park, MD.
Donázar, J. A., Hiraldo, F. and Bustamante, J. 1993. Factors influencing nest site selection, breeding density and breeding success in bearded vulture (Gypaetus barbatus). Journal of Applied Ecology, 30: 504–514.
Efron, B. and Tibshirani, R. 1997. Improvements on cross-validation: the.632+ bootstrap method. Journal of the American Statistical Association, 92: 548–506.
Fielding, A. H. and Bell, J. F. 1997. A review of methods for the assessment of prediction errors in conservation presence/absence models. Environmental Conservation, 24: 38–49.
Fielding, A. H. and Haworth, P. F. 1995. Testing the generality of bird-habitat models. Conservation Biology, 9: 1466–1481.
Forbes, A. D. 1995. Classification algorithm evaluation: five performance measures based on confusion matrices. Journal of Clinical Monitoring, 11: 189–206.
Guégan, J-F, Lek, S. and Oberdorff, T. 1998. Energy availability and habitat heterogeneity predict global riverine fish diversity. Nature, 391: 382–384.
Gordon, A. D. 1981. Classification: methods for the exploratory analysis of multivariate data. Chapman and Hall, London.
Hand, D. J. 1997. Construction and assessment of classification rules. Wiley, Chicester.
Henery, R. J. 1994. Classification. Pp 6–16 in D. Michie, D. J. Spiegelhalter and C. C. Taylor (eds) Machine learning, neural and statistical classification. Ellis Horwood, New York.
Huberty, C. J. 1994. Applied Discriminant Analysis. Wiley Interscience, New York.
Landis, J. R. and Koch, G. C. 1977. The measurement of observer agreement for categorical data. Biometrics, 33: 159–174.
Lin, T. C. and Pourhmadi, M. 1998. Nonparametric and non-linear models and data mining in time series: a case study on the Canadian lynx data. Applied Statistics, 47: 187–201.
Lynn, H., Mohler, C. L., DeGloria, S. D. and McCulloch, C. E. 1995, Error assessment in decision-tree models applied to vegetation analysis. Landscape Ecology, 10: 323–335.
Ma, Z. and Redmond, R. L. 1995. Tau coefficients for accuracy assessment of classifications of remote sensing data. Photogrammetric Engineering and Remote Sensing, 61: 435–439.
Madger, L. S. and Hughes, J. P. 1997. Logistic regression when the outcome is measured with uncertainty. Amer dan Journal of Epidemiology, 146: 195–203.
Marsden, S. and Fielding, A. H. In press. Habitat associations of parrots on the islands of Bum, Seram and Sumba. Journal of Biogeography.
Mastrorillo, S., Lek, S., Dauba, F. and Belaud, A. 1997. The use of artificial neural networks to predict the presence of small-bodied fish in a river. Freshwater Biology, 38: 237–246.
May, L. 1998. Vocalizations in the magpie and the corncrake: methods of analysis, individual differences and geographical variation (2 volumes). Unpublished PhD thesis, the Manchester Metropolitan University.
Michie, D., Spiegelhalter, D. J. and Taylor, C. C. 1994. Machine learning, neural and statistical classification. Ellis Horwood, New York.
Morrison, M. L., Timoss, I. C. and With, K. A. 1987. Development and testing linear regression models predicting bird-habitat relationships. Journal of Wildlife Management 51:247–253.
Morrison, M. L., Marcot, B. G. and Mannan, R. W. 1992. Wildlife Habitat Relationships. Concepts and Applications. University Wisconsin Press, Madison.
Osborne, P. E and Tigar, B. J. 1992. Interpreting bird atlas data using logistic models: an example from Lesotho, Southern Africa. Journal of Applied Ecology 29: 55–62.
Pereira, J. M. C. and Itami, R. C. 1991. GIS-based habitat modelling using logistic multiple regression: a study of the Mt. Graham red squirrel. Photogrammetric Engineering & Remote Sensing, 57: 1475–1486.
Provost, F. and Fawcett, T. 1997. Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions. Pp 43–48 in Proceedings of the Third International Conference on Knowledge Discovery and Data Mining (KDD-97). AAAI Press.
Reby, D., Joachim, J., Lauga, J., Lek, S. and Aulagnier, S 1998. Individuality in the groans of fallow deer (Dama dama) bucks. Journal of the Zoological Society of London, 245: 79–84.
Rencher, A. C. 1995. Methods of Multivariate Analysis. Wiley, New York.
Riordan, P. 1998. Unsupervised recognition of indivdual tigers and snow leopards from their footprints. Animal Conservation, 1: 253–262.
Ripley, B. D. 1994. Neural network and related methods for classification. Journal of the Royal Statistical Society, Series B, 56: 409–456.
Ruttiman, U. E. 1994. Statistical approaches to development and validation of predictive instruments. Critical Care Clinics 10: 19–35.
Salzberg, S. L. 1997. On comparing classifiers: Pitfalls to avoid and a recommended approach Data mining and knowledge discovery, 1:317–328
Schaafsma, W. and van Vark, G. N. 1979. Classification and discrimination problems with applications. Part Ha. Statistica Neerlandica, 33:91–126.
Schiffers, J. 1997. A classification approach incorporating misclassification costs. Intelligent Data Analysis, 1(1): an electronic journal http://www.elsevier.com/locate/ida
Turney, P. D. 1995. Cost-sensitive classification: empirical evaluation of a hybrid genetic decision tree induction algorithm. Journal of Artificial Intelligence Research, 2: 369–409.
Turney, P. D. 1998. Types of Cost. Accessed 21/10/98, document dated 28 April 1998 http://ai.iit.nrc.ca/bibliographies/cost-types.html
Verbyla, D. L. and Litvaitis, J. A. 1989. Resampling methods for evaluating classification accuracy of wildlife habitat models. Environmental Management, 13: 783–787.
Zweig, M. H. and Campbell, G. 1993. Receiver-Operating Characteristic (ROC) Plots: A fundamental evaluation tool in clinical medicine. Clinical Chemistry 39: 561–577.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media New York
About this chapter
Cite this chapter
Fielding, A. (1999). How should accuracy be measured?. In: Fielding, A.H. (eds) Machine Learning Methods for Ecological Applications. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-5289-5_8
Download citation
DOI: https://doi.org/10.1007/978-1-4615-5289-5_8
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-7413-8
Online ISBN: 978-1-4615-5289-5
eBook Packages: Springer Book Archive