"Mark Weber" <firstname.lastname@example.org> wrote:
>Help! I am new to ADE-4 and know very little French! I have a bio-physical
>data set with both qualitative and quantitative variables. I would like to
>run a Principal Componments Analysis on the data, but do not know which PCA
>method to use. Are any of the PCA methods in ADE-4 capable of analyzing both
>qualitative and quantitative data?
You can use the "Hill and Smith analysis" option in the MCA module.
Be sure to read the documentation before trying it :)
You can also transform the quantitative variables to qualitative (for example
with the Quant->Categ option in the CategVar module).
Or you can use the qualitative variables as if they were quantitative (if the
categories are at least ordered).
You can also use the binary indicators of the qualitative variables (with an
apropriate weighting to lessen the importance given to them)
Read ftp://pbil.univ-lyon1.fr/pub/mac/ADE/ADE4/DocThemPDF/Thema2B.pdf (only
in French, sorry...)
-- Jean Thioulouse - Laboratoire de Biometrie - Universite Lyon 1 69622 Villeurbanne Cedex - France Fax: 04 78 89 27 19 Tel: 04 72 43 29 01 http://pbil.univ-lyon1.fr/ADE-4/JTHome.html
This archive was generated by hypermail 2b30 : Sat Feb 10 2001 - 10:35:58 MET