[R] DOE support in R and fac.design

Prof Brian Ripley ripley at stats.ox.ac.uk
Sun Nov 16 23:51:42 CET 2003


On Sun, 16 Nov 2003, Nirmal Govind wrote:

> I've searched through the contributed packages and found conf.design 
> which supports factorial design generation - is there any way to specify 
> the values of the levels in the functions in this library? Currently the 
> default for 2 level designs are the levels 0 and 1. Reason I ask is I'd 
> like to create a Central Composite design and to do this by appending to 
> a factorial design, it would be easiest if the levels of the factorial 
> were at -1 and 1... (so I can add levels such as 0, -2 and 2)

It is very easy to change the levels of a factor by levels<-(): see its 
help page.

> This brings me to my second question - is there any support for design 
> creation of some of the common designs like the CCD?

charge-coupled device?  Probably central composite design -- not that I 
know of.

> And finally - in the help for conf.design, in the "See Also" section, 
> there's a fac.design mentioned but I can't seem to find it anywhere.. is 
> this function available and what does it do?

conf.design was ported from S, which does have fac.design.

-- 
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




More information about the R-help mailing list