Best Possible Constant for Bandwidth Selection

  title={Best Possible Constant for Bandwidth Selection},
  author={Jianqing Fan and J. S. Marron},
For the data based choice of the bandwidth of a kernel density estimator, several methods have recently been proposed which have a very fast asymptotic rate of convergence to the optimal bandwidth. In the particular the relative rate of convergence is the square root of the sample size, which is known to be the possible. The point of this paper is to show how semiparametric arguments can be employed to calculate the best possible constant coefficient, i.e. an analog of the usual Fisher… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 13 references

Efficient and Adaptive Inference in Semi-parametric Models. Forthcoming monograph

P. J. Bickel, C.A.J. Klassen, Y. Ritov, J. A. Wellner
View 9 Excerpts
Highly Influenced

Contributions to the estimation ofnonregular functionals

J. Fan
View 1 Excerpt
Highly Influenced

Bandwidth selection for kernel density estimation, Ann

S. T. Chiu
View 2 Excerpts

Applied Nonparametric Regression

W. HardIe
View 1 Excerpt

Exact mean integrated squared error

J. S. Marron, M. P. Wand
Manuscript . • 1990

Lower bounds for bandwidth selection in density estimation

P. Hall, J. S. Marron
Probability Theory and Related Fields, • 1990
View 1 Excerpt

One the estimation of quadratic functionals

J. Fan
Ann. Statist., • 1990
View 1 Excerpt

Using nonstochastic terms to advantage in kernel based estimation of integrated squared density derivatives

M. C. Jones, S. J. Sheather
Unpublished manuscript . • 1990
View 1 Excerpt

Automatic smoothing parameter selection : a survey

J. S. Marron
Empirical Economics • 1988
View 1 Excerpt

Similar Papers

Loading similar papers…