Data-Driven Smoothing Based on Convexity Properties

A theorem on uniform convergence for densities with a fixed number of inflection points is proved. As an application, a method of automatic choice of bandwidth parameters in density estimation is proposed. It is based on the idea of making equal the numbers of inflection points of the estimates and that of the target density. The resulting estimates are almost surely uniformly consistent. This method is closely connected with previous ideas of Silverman (1981, 1983) and provides, in many practical situations, a natural procedure for the bump-hunting problem. A Monte Carlo study is included.

[1]  Dennis D. Boos,et al.  A Converse to Scheffe's Theorem , 1985 .

[2]  B. Silverman Density estimation for statistics and data analysis , 1986 .

[3]  David G. Kendall,et al.  Spline Transformations: Three New Diagnostic Aids for the Statistical Data‐Analyst , 1971 .

[4]  L. A. Klimko,et al.  A Note on the Strong Convergence of Distributions , 1974 .

[5]  A. Bowman An alternative method of cross-validation for the smoothing of density estimates , 1984 .

[6]  J. F. C. Kingman,et al.  Probability, statistics, and analysis , 1983 .

[7]  W. Chan,et al.  Unimodality, convexity, and applications , 1989 .

[8]  B. W. Silverman,et al.  Probability, Statistics and Analysis: Some properties of a test for multimodality based on kernel density estimates , 1983 .

[9]  C. J. Stone,et al.  An Asymptotically Optimal Window Selection Rule for Kernel Density Estimates , 1984 .

[10]  Peter Hall,et al.  Using the bootstrap to estimate mean squared error and select smoothing parameter in nonparametric problems , 1990 .

[11]  P. Hall On Kullback-Leibler loss and density estimation , 1987 .

[12]  D. W. Scott,et al.  Biased and Unbiased Cross-Validation in Density Estimation , 1987 .

[13]  D. A. Sprott,et al.  Foundations of Statistical Inference. , 1972 .

[14]  I. Good,et al.  Density Estimation and Bump-Hunting by the Penalized Likelihood Method Exemplified by Scattering and Meteorite Data , 1980 .

[15]  R. Reiss On the Measurability and Consistency of Maximum Likelihood Estimates for Unimodal Densities , 1973 .

[16]  P. McMullen Convex Sets and Their Applications , 1982 .

[17]  L. Devroye A Course in Density Estimation , 1987 .

[18]  T. Hettmansperger On the Trimmed Mann-Whitney Statistic , 1968 .

[19]  Trevor J. Sweeting,et al.  On a Converse to Scheffe's Theorem , 1986 .

[20]  Luc Devroye,et al.  On the Relationship Between Stability of Extreme Order Statistics and Convergence of the Maximum Likelihood Kernel Density Estimate , 1989 .

[21]  P. Billingsley,et al.  Convergence of Probability Measures , 1969 .

[22]  P. Bickel On Some Robust Estimates of Location , 1965 .

[23]  B. Silverman,et al.  Weak and Strong Uniform Consistency of the Kernel Estimate of a Density and its Derivatives , 1978 .

[24]  James Stephen Marron,et al.  A Comparison of Cross-Validation Techniques in Density Estimation , 1987 .