Plsnipal: Difference between revisions

From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search
imported>Jeremy
(Importing text file)
imported>Chuck
No edit summary
Line 1: Line 1:
===Purpose===
===Purpose===


Calculate single latent variables for partial least squares regression.
Calculate a single latent variable for partial least squares regression (PLS).


===Synopsis===
===Synopsis===
Line 10: Line 9:
===Description===
===Description===


PLSNIPAL is called by the routine pls to calculate each latent variable in a partial least squares regression.
PLSNIPAL is called by the routine [[pls]] to calculate each latent variable in a partial least squares regression.
 
====Inputs====
 
* '''x''' = x-block input data (for first PLS latent variable), or x-block residuals (for subsequent latent variables)
* '''y''' = y-block input data (for first PLS latent variable), or y-block residuals (for subsequent latent variables)


Inputs x and y are either the x-block and y-block for calculation of the first latent variable, or the x-block and y-block residuals for calculation of subsequent latent variables.
====Outputs====


The outputs are p the x-block latent variable loadings, q the y-block variable loadings, w the x-block latent variable weights, t the x-block latent variable scores, and u the y-block latent variable scores.
* '''p''' = x-block latent variable loadings  
* '''q''' = y-block latent variable loadings
* '''w''' = x-block latent variable weights
* '''t''' = x-block latent variable scores
* '''u''' = y-block latent variable scores


===See Also===
===See Also===


[[nippls]], [[pls]], [[analysis]], [[simpls]]
[[nippls]], [[pls]], [[analysis]], [[simpls]]

Revision as of 21:03, 8 October 2008

Purpose

Calculate a single latent variable for partial least squares regression (PLS).

Synopsis

[p,q,w,t,u] = plsnipal(x,y)

Description

PLSNIPAL is called by the routine pls to calculate each latent variable in a partial least squares regression.

Inputs

  • x = x-block input data (for first PLS latent variable), or x-block residuals (for subsequent latent variables)
  • y = y-block input data (for first PLS latent variable), or y-block residuals (for subsequent latent variables)

Outputs

  • p = x-block latent variable loadings
  • q = y-block latent variable loadings
  • w = x-block latent variable weights
  • t = x-block latent variable scores
  • u = y-block latent variable scores

See Also

nippls, pls, analysis, simpls