Statistics and Computing

, Volume 5, Issue 3, pp 245–252

A simple, automatic and adaptive bivariate density estimator based on conditional densities

  • Jeffrey S. Simonoff


The standard approach to non-parametric bivariate density estimation is to use a kernel density estimator. Practical performance of this estimator is hindered by the fact that the estimator is not adaptive (in the sense that the level of smoothing is not sensitive to local properties of the density). In this paper a simple, automatic and adaptive bivariate density estimator is proposed based on the estimation of marginal and conditional densities. Asymptotic properties of the estimator are examined, and guidance to practical application of the method is given. Application to two examples illustrates the usefulness of the estimator as an exploratory tool, particularly in situations where the local behaviour of the density varies widely. The proposed estimator is also appropriate for use as a ‘pilot’ estimate for an adaptive kernel estimate, since it is relatively inexpensive to calculate.


Kernel density estimation smoothing parameter selection 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abramson, I. S. (1982) On bandwidth variation in kernel estimates—a square root law. Annals of Statistics, 10, 1217–1223.Google Scholar
  2. Fan, J. and Marron, J. S. (1994) Fast implementations of non-parametric curve estimators. Journal of Computational and Graphical Statistics, 3, 35–56.Google Scholar
  3. Flury, B. and Riedwyl, H. (1988) Multivariate statistics: a practical approach. Chapman & Hall, London.Google Scholar
  4. IMSL (1989) Stat/Library Version 1.1. IMSL, Houston.Google Scholar
  5. Jones, M. C., Marron, J. S. and Sheather, S. J. (1992) Progress in data-based bandwidth selection for kernel density estimation. Unpublished manuscript.Google Scholar
  6. Marron, J. S. (1993) Assessing bandwidth selectors with visual error criteria. Unpublished manuscript.Google Scholar
  7. Marron, J. S. and Tsybakov, A. B. (1993) Visual error criteria for qualitative smoothing. Unpublished manuscript.Google Scholar
  8. Park, B. U. and Turlach, B. A. (1992) Practical performance of several data driven bandwidth selectors (with discussion). Computational Statistics, 7, 251–270; 275–277; 283–285.Google Scholar
  9. Scott, D. W. (1992) Multivariate density estimation: theory, practice and visualization, Wiley, New York.Google Scholar
  10. Scott, D. W., Gotto, A. M., Cole, J. S. and Gorry, G. A. (1978) Plasma lipids as collateral risk factors in coronary heart disease—a study of 371 males with chest pain. Journal of Chronic Diseases, 31, 337–345.Google Scholar
  11. Sheather, S. J. (1992) The performance of six popular bandwidth selection methods on some real data sets (with discussion). Computational Statistics, 7, 255–250; 271–281.Google Scholar
  12. Sheather, S. J. and Jones, M. C. (1991) A reliable data-based bandwidth selection method for kernel density estimation. Journal of the Royal Statistical Society, Series B, 53, 683–690.Google Scholar
  13. Silverman, B. W. (1986) Density estimation for statistics and data analysis. Chapman & Hall, New York.Google Scholar
  14. Simonoff, J. S. (1983) A penalty function approach to smoothing large sparse contingency tables. Annals of Statistics, 11, 208–218.Google Scholar
  15. Simonoff, J. S. (1987) Probability estimation via smoothing in sparse contingency tables. Statistics and Probability Letters, 5, 55–63.Google Scholar
  16. Simonoff, J. S. (1993) The anchor position of histograms and frequency polygons: quantitative and qualitative smoothing. NYU Stat/OR Department Working Paper #93-8.Google Scholar
  17. Statistical Sciences, Inc. (1993) S-PLUS for Windows User's Manual, Version 3.1. Statistical Sciences, Inc., Seattle.Google Scholar
  18. Terrell, G. R. and Scott, D. W. (1992) Variable kernel density estimation. Annals of Statistics, 20, 1236–1265.Google Scholar
  19. Wand, M. P. and Jones, M. C. (1993) Comparison of smoothing parametrizations in bivariate kernel density estimation. Journal of the American Statistical Association, 88, 520–528.Google Scholar
  20. Wand, M. P. and Jones, M. C. (1994) Multivariate plug-in bandwidth selection. Computational Statistics, 9, 97–116.Google Scholar

Copyright information

© Chapman & Hall 1995

Authors and Affiliations

  • Jeffrey S. Simonoff
    • 1
  1. 1.Department of Statistics and Operations ResearchNew York UniversityNew YorkUSA

Personalised recommendations