[R] pca scores for newdata

[Prof Brian Ripley]

On Mon, 1 Mar 2004, Christoph Lehmann wrote:

> I used princomp on a dataset x[!sub,]. How can I get the scores for
> another dataset, say x[sub,]? I didn't succeed using predict()

What did you try?  Whatever it was, predict() is the correct idea:

> data(USArrests)
> pc.cr <- princomp(USArrests, cor = TRUE)
> predict(pc.cr, USArrests[1:10,])
             
                   Comp.1      Comp.2      Comp.3       Comp.4
  Alabama      0.98556588  1.13339238 -0.44426879  0.156267145
  Alaska       1.95013775  1.07321326  2.04000333 -0.438583440
  Arizona      1.76316354 -0.74595678  0.05478082 -0.834652924
  Arkansas    -0.14142029  1.11979678  0.11457369 -0.182810896
  California   2.52398013 -1.54293399  0.59855680 -0.341996478
  Colorado     1.51456286 -0.98755509  1.09500699  0.001464887
  Connecticut -1.35864746 -1.08892789 -0.64325757 -0.118469414
  Delaware     0.04770931 -0.32535892 -0.71863294 -0.881977637
  Florida      3.01304227  0.03922851 -0.57682949 -0.096284752
  Georgia      1.63928304  1.27894240 -0.34246008  1.076796812

based on the example on the help page.

-- 
Brian D. Ripley,                  ripley at stats.ox.ac.uk
Professor of Applied Statistics,  http://www.stats.ox.ac.uk/~ripley/
University of Oxford,             Tel:  +44 1865 272861 (self)
1 South Parks Road,                     +44 1865 272866 (PA)
Oxford OX1 3TG, UK                Fax:  +44 1865 272595