Super reduce

From Eigenvector Research Documentation Wiki
Revision as of 13:02, 10 October 2008 by imported>Jeremy (New page: ===Purpose=== Eliminates highly correlated variables. ===Synopsis=== :corr_values=super_reduce(data,level_corr); ===Description=== When several variables have a high correlation, the...)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

Purpose

Eliminates highly correlated variables.

Synopsis

corr_values=super_reduce(data,level_corr);

Description

When several variables have a high correlation, the variable(s) with the lower intensity will be deleted, leaving the most intense variable.

Generally used in combination with CODA and COMPARLCMS applications.

Inputs

  • data = matrix to be analyzed or a dataset object. Only included rows and columns will be analyzed

Optional Inputs

  • level_corr = sets the correlation level above which variables will be eliminated. A plot will be made when level_corr is given.

Outputs

  • corr_val = correlation values used for elimination.

See Also

coda_dw, comparelcms_sim_interactive