Skip to main content
SpringerLink
Log in

A possible pitfall in the morphometric application of discriminant analysis: measurement bias

  • Published:
Marine Biology Aims and scope Submit manuscript

Abstract

Standard methods of evaluating the effectiveness of a discriminant analysis do not include an examination of the possible effect of measurement errors. An example (based on squid-beak morphometrics) is given, where a relatively small degree of bias could reduce the probability of correct classification of one species from 89% to less than 50%. This is used to illustrate a general procedure for evaluating the extent of bias in morphometric measurements and its potential effect on a discriminant function. It is recommended that such a procedure be part of the evaluation of any published discriminant based on morphometrics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Literature cited

  • Aitchison, J.: A calibration problem in statistical diagnosis: the system transfer problem. Biometrika 64, 461–472 (1977)

    Google Scholar 

  • Aitchison, J.: A calibration problem in statistical diagnosis: the clinic amalgamation problem. Biometrika 66, 357–366 (1979)

    Google Scholar 

  • Aitchison, J. and I. J. Lauder: Statistical diagnosis from imprecise data. Biometrika 66, 475–483 (1979)

    Google Scholar 

  • Blackith, R. E. and R. A. Reyment: Multivariate morphometrics, 412 pp. London: Academic Press 1971

    Google Scholar 

  • Broffitt, B., W. R. Clarke and P. A. Lachenbruch: Measurement errors — a location contamination problem in discriminant analysis. Communs Statist. (B: Simulation and Computation) 10, 129–141 (1981)

    Google Scholar 

  • Kawakami, T. and T. Okutani: A note on identity of ommastrephid squids of the genus Nototodarus exploited in the New Zealand waters. Bull. Tokai reg. Fish Res. Lab. 105, 17–30 (1981)

    Google Scholar 

  • Lachenbruch, P. A. and M. Goldstein: Discriminant analysis. Biometrics 35, 69–85 (1979)

    Google Scholar 

  • Mercer, M. C., R. K. Misra and G. V. Hurley: Sex determination of the ommastrephid squid Illex illecebrosus using beak morphometrics. Can. J. Fish. aquat. Sciences. 37, 283–286 (1980)

    Google Scholar 

  • Smith, P. J., P. E. Roberts and R. J. Hurst: Evidence for two species of arrow squid in the New Zealand fishery. N.Z. Jl mar. Freshwat. Res. 15, 247–253 (1981)

    Google Scholar 

  • Wolff, G. A. and J. H. Wormuth: Biometric separation of the beaks of two morphologically similar species of the squid family Ommastrephidae. Bull. mar. Sci. 29, 587–592 (1979)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Fisheries Research Centre, Ministry of Agriculture and Fisheries, P.O. Box 297, Wellington, New Zealand

    R. I. C. C. Francis & R. H. Mattlin

Authors
  1. R. I. C. C. Francis
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. R. H. Mattlin
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Communicated by G. F. Humphrey, Sydney

Rights and permissions

Reprints and permissions

About this article

Cite this article

Francis, R.I.C.C., Mattlin, R.H. A possible pitfall in the morphometric application of discriminant analysis: measurement bias. Mar. Biol. 93, 311–313 (1986). https://doi.org/10.1007/BF00508269

Download citation

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00508269

Keywords

Search

Navigation