Multivariate kernel density estimation: Difference between revisions

Revision as of 14:30, 12 February 2013

Revision as of 20:45, 19 May 2013

Line 114:

The code fragment computes the kernel density estimate with the plug-in bandwidth matrix <math>\hat{\bold{H}}_\operatorname{PI} = \begin{bmatrix}0.052 & 0.510 \\ 0.510 & 8.882\end{bmatrix}.</math> Again, the coloured contours correspond to the smallest region which contains the respective probability mass: red = 25%, orange + red = 50%, yellow + orange + red = 75%. To compute the SCV selector, <code>Hpi</code> is replaced with <code>Hscv</code>. This is not displayed here since it is mostly similar to the plug-in estimate for this example.

<presource lang="rsplus" style="overflow:auto;">

library(ks)

data(faithful)

Line 121:

plot(fhat, display="filled.contour2")

points(faithful, cex=0.5, pch=16)

</presource>

==Density estimation in R with a diagonal bandwidth matrix==

Line 136:

prompt by using copy and paste.

<presource lang="rsplus" style="overflow:auto;">

library(np)

library(datasets)

Line 142:

f <- npudens(~eruptions+waiting,data=faithful)

plot(f,view="fixed",neval=100,phi=30,main="",xtrim=-0.2)

</presource>

Computing kernel density estimates with diagonal bandwidth selectors is also available in the <tt>ks</tt> library, using the <tt>Hpi.diag()</tt> function. To produce a 3D plot similar to that from <tt>npudens()</tt>, the option <tt>display="persp"<tt> is added.

<presource lang="rsplus" style="overflow:auto;">

library(ks)

data(faithful)

Line 151 ⟶ 152:

fhat <- kde(x=faithful, H=H)

plot(fhat, display="persp")

</presource>

==Density estimation in Matlab with a diagonal bandwidth matrix==

Line 185 ⟶ 186:

in the current directory.

<presource lang="matlab" style="overflow:auto;">

clear all

% generate synthetic data

Line 195 ⟶ 196:

contour3(X,Y,density,50), hold on

plot(data(:,1),data(:,2),'r.','MarkerSize',5)

</presource>

===Alternative optimality criteria===