See ?AlgDesign::optFederov and look for the 'Value' section, where these elements of the output list are defined.
Dennis On Wed, Nov 23, 2011 at 7:15 PM, 蓁蓁 李 <tszhenzh...@hotmail.com> wrote: > > Hi, > > I am wondering how I should interpreate the output of optFederov() in > AlgDesign. > > Specially I want to know what is $D, $A, $Ge and $Dea, which one I can use as > an efficiency to say how good the optimal design is. > > I only know when a orthogonal design comes, $D = 1. > > I red the pdf document -- vignette("AlgDesign") > > [Just type: vignette("AlgDesign") in R, you will get this pdf document] > > On page 20 section 4.2.1.3, it says: the D and G efficiencies of the > following ... are 98% and 89%. > > I tried the code as shown on page 20 a few times and output showed different > designs but the figure of $D, $A, $Ge and $Dea are similar. I don't see $D is > close to 0.98, but $Ge is 0.89. One of the output as below: > > > > >> dat = gen.factorial(3, 3, center = T, varNames = c("A", "B", "C")) >> desC = optFederov(~quad(A,B,C), dat, nT = 14, evaluateI = T, nR = 100) >> desC > $D > [1] 0.4630447 > > $A > [1] 3.22 > > $I > [1] 9.945833 > > $Ge > [1] 0.893 > > $Dea > [1] 0.887 > > $design > A B C > 1 -1 -1 -1 > 3 1 -1 -1 > 5 0 0 -1 > 7 -1 1 -1 > 9 1 1 -1 > 11 0 -1 0 > 13 -1 0 0 > 15 1 0 0 > 17 0 1 0 > 19 -1 -1 1 > 21 1 -1 1 > 23 0 0 1 > 25 -1 1 1 > 27 1 1 1 > > $rows > [1] 1 3 5 7 9 11 13 15 17 19 21 23 25 27 > > Thanks very much! > J > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.