Advertisement

Some suggestions for measuring predictive performance

  • Lewis B. Sheiner
  • Stuart L. Beal
Scientific Commentary

Abstract

The performance of a prediction or measurement method is often evaluated by computing the correlation coefficient and/or the regression of predictions on true (reference) values. These provide, however, only a poor description of predictive performance. The mean squared prediction error (precision) and the mean prediction error (bias) provide better descriptions of predictive performance. These quantities are easily computed, and can be used to compare prediction methods to absolute standards or to one another. The measures, however, are unreliable when the reference method is imprecise. The use of these measures is discussed and illustrated.

Key words

predictions errors measurement statistics precision bias 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    W. J. Dixon and F. J. Massey.Introduction to Statistical Analysis, 3rd ed., McGraw-Hill, New York, 1969, p. 98.Google Scholar
  2. 2.
    R. G. Miller. The jacknife—A review.Biometrika 61:1–15 (1974).Google Scholar
  3. 3.
    W. J. Dixon and F. J. Massey.Introduction to Statistical Analysis, 3rd ed., McGraw-Hill, New York, 1969, p. 349.Google Scholar
  4. 4.
    W. J. Dixon and F. J. Massey.Introduction to Statistical Analysis, 3rd ed., McGraw-Hill, New York, 1969, pp. 341–342.Google Scholar

Copyright information

© Plenum Publishing Corporation 1981

Authors and Affiliations

  • Lewis B. Sheiner
    • 1
  • Stuart L. Beal
    • 1
  1. 1.Department of Laboratory Medicine, and Department of Medicine, Division of Clinical PharmacologyUniversity of CaliforniaSan Francisco

Personalised recommendations