search for: lmescal

I am using package nlme and would like to specify initial values for a linear mixed-effects model to help with convergence. I am trying to specify those initial values using the msScale option under ?control? in the lme() function: lme(Y ~ X1, random= ~ X1|X2, control=list(msScale=lmeScale)) where, (as far as I understand), lmeScale is a function that can take initial values for parameters. However, I am unsure about how to input those starting values (e.g., what names lme will recognize for fixed and random effects, in what format, and if a partial list of initial values would be...

...fitting of the model works mathematically) I was wondering if anyone knew if there was anything else in the control values I should try changing. Below are the defaults.. lmeControl function (maxIter = 50, msMaxIter = 50, tolerance = 1e-06, niterEM = 25, msTol = 1e-07, msScale = lmeScale, msVerbose = FALSE, returnObject = FALSE, gradHess = TRUE, apVar = TRUE, .relStep = (.Machine$double.eps)^(1/3), minAbsParApVar = 0.05, nlmStepMax = 100, optimMethod = "BFGS", natural = TRUE) I was reading on the R listserve that lmer from the lme4 package may be pref...

...from anyone who has an idea on what parameters in gnlsControl to change to get convergence. Cheers Dan Coleman Genentech Inc. > gnlsControl function (maxIter = 50, nlsMaxIter = 7, msMaxIter = 50, minScale = 0.001, tolerance = 1e-06, nlsTol = 0.001, msTol = 1e-07, msScale = lmeScale, returnObject = FALSE, msVerbose = FALSE, apVar = TRUE, .relStep = (.Machine$double.eps)^(1/3), nlmStepMax = 100, opt = c("nlminb", "optim"), optimMethod = "BFGS", minAbsParApVar = 0.05) { list(maxIter = maxIter, nlsMaxIter = nlsMaxIter, msMax...

Dear all, Is there any generic algorithm code for optimization implemented in R? I searched without success. Thanks, -- Zhu Wang Statistical Science Department Southern Methodist University Phone: (214)768-2453 Fax: (214)768-4035 Email: zhuw at mail.smu.edu

I don't want to re-invent the wheel, and I'm trying to code up something that does a Nelder-Mead simplex method to minimise a non-linear objective function. (I'm porting something I originally wrote in matlab, using the optimisation toolbox funciton fmins). Is there already something available to do this included in R? Do people have suggestions on the best way to do this? Thanks,

...Value p-value (Intercept) 45.12417 <.0001 X1 6.04350 <.0001 X2 6.25833 0.0709 X1:X2 0.40417 0.8299 Number of Observations: 60 Number of Groups: 3 I have examined the help.start() HTML pages and the lmeScale( ) function looks helpful, but I don't know how to use it to tell R to use a particular set of starting values for the params. It would have been instructive to see what happens if the same starting values are specified for both Splus and R.... Below is a sample dataset that is fairly close t...