Ewfa: Difference between revisions
Jump to navigation
Jump to search
imported>Jeremy (Importing text file) |
imported>Bob No edit summary |
||
| Line 1: | Line 1: | ||
===Purpose=== | ===Purpose=== | ||
| Line 10: | Line 9: | ||
===Description=== | ===Description=== | ||
The inputs are the data matrix dat and the window | The inputs are the data matrix <tt>dat</tt> and the window width <tt>window</tt>. The output <tt>eigs</tt> contains the eigenvalues for each window. The windowed eigenvalues vs. sample number is also plotted. Note that the eigenvalues on the ends of the record (less than the half width of the window) are plotted as dashed lines. The output <tt>skl</tt> is a scale that can be used to plot <tt>eigs</tt> against. | ||
Optional input <tt>plots</tt> can be used to suppress plotting when set to 0 {default <tt>plots</tt> = 1}. Optional input <tt>scl</tt> is a scale to plot against. It is also used to construct a new <tt>skl</tt>. | |||
====Inputs==== | |||
* '''dat''' = input x-block, double array. | |||
* '''window''' = window width. | |||
====Optional Inputs==== | |||
* '''plots''' = [ 0 | {1} ] - 0 suppresses plots. | |||
* '''scl''' = scale to plot <tt>eigs</tt> against. | |||
====Outputs==== | |||
* '''eigs''' = singular values for each window. | |||
* '''skl''' = scale to plot <tt>eigs</tt> against. | |||
===See Also=== | ===See Also=== | ||
[[evolvfa]], [[pca]], [[wtfa]] | [[evolvfa]], [[pca]], [[wtfa]], [[mcr]], [[mpca]], [[pcaengine]] | ||
Revision as of 07:28, 9 October 2008
Purpose
Evolving window factor analysis.
Synopsis
- [eigs,skl] = ewfa(dat,window,plots,scl)
Description
The inputs are the data matrix dat and the window width window. The output eigs contains the eigenvalues for each window. The windowed eigenvalues vs. sample number is also plotted. Note that the eigenvalues on the ends of the record (less than the half width of the window) are plotted as dashed lines. The output skl is a scale that can be used to plot eigs against.
Optional input plots can be used to suppress plotting when set to 0 {default plots = 1}. Optional input scl is a scale to plot against. It is also used to construct a new skl.
Inputs
- dat = input x-block, double array.
- window = window width.
Optional Inputs
- plots = [ 0 | {1} ] - 0 suppresses plots.
- scl = scale to plot eigs against.
Outputs
- eigs = singular values for each window.
- skl = scale to plot eigs against.