Significance in Scale Space for Bivariate Density Estimation
- 1 March 2002
- journal article
- Published by Taylor & Francis in Journal of Computational and Graphical Statistics
- Vol. 11 (1) , 1-21
- https://doi.org/10.1198/106186002317375596
Abstract
An important problem in the use of density estimation for data analysis is whether or not observed features, such as bumps, are “really there” as opposed to being artifacts of the natural sampling variability. Here we propose a solution to this problem, in the challenging two-dimensional case, using the graphical technique of significance in scale space. Color and dynamic graphics form an important part of the visualization method.Keywords
This publication has 10 references indexed in Scilit:
- Scale space view of curve estimationThe Annals of Statistics, 2000
- SiZer for Exploration of Structures in CurvesJournal of the American Statistical Association, 1999
- Interactive local bandwidth choiceStatistics and Computing, 1999
- Estimating and Visualizing Conditional DensitiesJournal of Computational and Graphical Statistics, 1996
- Computing and Graphing Highest Density RegionsThe American Statistician, 1996
- A Brief Survey of Bandwidth Selection for Density EstimationJournal of the American Statistical Association, 1996
- Facts about the gaussian probability density functionApplicable Analysis, 1995
- High interaction graphicsEuropean Journal of Operational Research, 1995
- A Look at Some Data on the Old Faithful GeyserJournal of the Royal Statistical Society Series C: Applied Statistics, 1990
- Representation and display of vector field topology in fluid flow data setsComputer, 1989