Attributing a probability to the shape of a probability density
From MaRDI portal
Abstract: We discuss properties of two methods for ascribing probabilities to the shape of a probability distribution. One is based on the idea of counting the number of modes of a bootstrap version of a standard kernel density estimator. We argue that the simplest form of that method suffers from the same difficulties that inhibit level accuracy of Silverman's bandwidth-based test for modality: the conditional distribution of the bootstrap form of a density estimator is not a good approximation to the actual distribution of the estimator. This difficulty is less pronounced if the density estimator is oversmoothed, but the problem of selecting the extent of oversmoothing is inherently difficult. It is shown that the optimal bandwidth, in the sense of producing optimally high sensitivity, depends on the widths of putative bumps in the unknown density and is exactly as difficult to determine as those bumps are to detect. We also develop a second approach to ascribing a probability to shape, using Muller and Sawitzki's notion of excess mass. In contrast to the context just discussed, it is shown that the bootstrap distribution of empirical excess mass is a relatively good approximation to its true distribution. This leads to empirical approximations to the likelihoods of different levels of ``modal sharpness, or ``delineation, of modes of a density. The technique is illustrated numerically.
Recommendations
Cites work
- scientific article; zbMATH DE number 3599313 (Why is no real title available?)
- scientific article; zbMATH DE number 3619167 (Why is no real title available?)
- scientific article; zbMATH DE number 469135 (Why is no real title available?)
- scientific article; zbMATH DE number 2148863 (Why is no real title available?)
- scientific article; zbMATH DE number 3795187 (Why is no real title available?)
- scientific article; zbMATH DE number 837911 (Why is no real title available?)
- scientific article; zbMATH DE number 850144 (Why is no real title available?)
- A penalty function approach to smoothing large sparse contingency tables
- An approximation of partial sums of independent RV's, and the sample DF. II
- Applied Linear Regression
- Asymptotic distributions of slope-of-greatest-convex-minorant estimators
- Calibrating the Excess Mass and Dip Tests of Modality
- Conditional Minimum Volume Predictive Regions for Stochastic Processes
- Data features1
- Density Estimation and Bump-Hunting by the Penalized Likelihood Method Exemplified by Scattering and Meteorite Data
- Density estimation under qualitative assumptions in higher dimensions
- Excess Mass Estimates and Tests for Multimodality
- Local extremes, runs, strings and multiresolution. (With discussion)
- Locally adaptive regression splines
- Miscellanea. Data sharpening as a prelude to density estimation
- Mode testing in difficult cases
- Mode testing via the excess mass estimate
- On Qualitative Smoothness of Kernel Density Estimates1
- On a Class of m out of n Bootstrap Confidence Intervals
- On correcting for variance inflation in kernel density estimation
- On the calibration of Silverman's test for multimodality
- One-sided inference about functionals of a density
- Scale space view of curve estimation.
- SiZer for Exploration of Structures in Curves
- Some asymptotics for multimodality tests based on kernel density estimates
- Subsampling
- Testing for multimodality
- The dip test of unimodality
- The problem of regions
- The shape of kernel density estimates in higher dimensions
- The silhouette, concentration functions and ML-density estimation under order restrictions.
Cited in
(2)
This page was built for publication: Attributing a probability to the shape of a probability density
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1766129)
