Snv

From Eigenvector Research Documentation Wiki
Revision as of 13:35, 9 October 2008 by imported>Jeremy
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Purpose

Standard Normal Variate scaling.

Synopsis

[xcorr,mns,sds] = snv(x,options); %perform snv scaling
x = snv(xcorr,mns,sds); %undo snv

Description

Scales rows of the input x to be mean zero and unit standard deviation. This is the same as autoscaling the transpose of x.

Inputs

  • x = M by N matrix of data to be scaled (class "double" or "dataset").

Optional Inputs

  • options = options structure passed to function "auto" when performing SNV scaling. See auto.m for available options (not valid for undo operation).
  • mns = a vector of length M of means, and
  • sds = vector of length M of standard deviations.

Outputs

  • xcorr = the scaled data (xcorr will be the same class as x),
  • mns = vector of means for each row, and
  • sds = vector of standard deviations for each row.

To rescale or "undo" SNV, inputs are xcorr, mns, and sds from a previous SNV call. The output will be the original x.

See Also

auto, normaliz, preprocess