2007
DOI: 10.18637/jss.v021.i07
|View full text |Cite
|
Sign up to set email alerts
|

ks: Kernel Density Estimation and Kernel Discriminant Analysis for Multivariate Data inR

Abstract: Kernel smoothing is one of the most widely used non-parametric data smoothing techniques. We introduce a new R package ks for multivariate kernel smoothing. Currently it contains functionality for kernel density estimation and kernel discriminant analysis. It is a comprehensive package for bandwidth matrix selection, implementing a wide range of data-driven diagonal and unconstrained bandwidth selectors.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
455
0
4

Year Published

2012
2012
2018
2018

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 559 publications
(459 citation statements)
references
References 14 publications
0
455
0
4
Order By: Relevance
“…4), we used twodimensional kernel density estimation 258 . Because results depend on the choice of the bandwidth used for the smoothing kernel, we used unconstrained bandwidth selectors 259 . To visualize the occurrence probability of a given trait combination in the PCA space as well as for all possible bivariate trait combinations, we constructed contour plots from two-dimensional kernel density distributions.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…4), we used twodimensional kernel density estimation 258 . Because results depend on the choice of the bandwidth used for the smoothing kernel, we used unconstrained bandwidth selectors 259 . To visualize the occurrence probability of a given trait combination in the PCA space as well as for all possible bivariate trait combinations, we constructed contour plots from two-dimensional kernel density distributions.…”
Section: Methodsmentioning
confidence: 99%
“…4 correspond to the 0.5, 0.95 and 0.99 quantiles of the respective probability distribution, thus highlighting the regions of highest and lowest trait occurrence probability. For kernel density estimation we used the 'kde' function and for optimal bandwidth selection carried out for each trait combination separately, we used the SAMSE pilot bandwidth selector 260 , both implemented in the R-package 'ks' 259 . The R script used is provided at ftp://pbil.univ-lyon1.fr/pub/datasets/dray/Diaz_Nature/.…”
Section: Methodsmentioning
confidence: 99%
“…Only well-defined single particles with intact DNA were selected for further analysis. Measured L values were processed with kernel density analysis using the package for R (61). Local minima of the density distribution of L values were used to separate the nucleosome structures into groups (see sections 2.3 and 2.4 in the Supporting Material).…”
Section: Experiment: Afm Visualization and Analysis Of The Pansmentioning
confidence: 99%
“…To do this, we developed both 50 and 95% 3-D penguin UDs. We included only foraging locations for all individuals combined and a 3-D kernel estimator using the 'ks' package (Duong 2013) in R. Kernels were smoothed using the default bandwidth selector (Gitzen et al 2006, Duong 2007.…”
Section: -D Kernel Udmentioning
confidence: 99%