[R] Regression and fitting

[ONKELINX, Thierry]

Try to set your own starting values. Use the values that you would expect for S0, mu and sigma.

HTH,

Thierry


----------------------------------------------------------------------------
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest
Cel biometrie, methodologie en kwaliteitszorg / Section biometrics, methodology and quality assurance
Gaverstraat 4
9500 Geraardsbergen
Belgium 
tel. + 32 54/436 185
Thierry.Onkelinx op inbo.be 
www.inbo.be 

To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of.
~ Sir Ronald Aylmer Fisher

The plural of anecdote is not data.
~ Roger Brinner

The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey

-----Oorspronkelijk bericht-----
Van: r-help-bounces op r-project.org [mailto:r-help-bounces op r-project.org] Namens Gunther Höning
Verzonden: dinsdag 1 juli 2008 14:41
Aan: R-help op r-project.org
Onderwerp: [R] Regression and fitting

Dear list,

I have some values like
Time	2	4		8		24		48	72

UTR	82543	169105	207615	96633		31988	7005
UTRs	82687	172934	205541	101842	31898	6950
of a twice repeated meassurement.

I know that the underlying function is of :

f(x) =  SO/(sqrt(2*pi)*sigma *x) * exp(-(S0*ln x - mu)^2/(2*sigma^2)).

How can I determine the value of S0, sigma and mu.

I tried nls:

lognormal <- function(x,S0,sigma,mu) {S0/(sqrt(2*pi)*sigma *x) *
exp(-(S0*log (x) - mu)^2/(2*sigma^2))}
x <- rep(c(2,4,6,24,48,72),2)
y <-
c(82543,169105,207615,96633,31988,7005,82687,172934,205541,101842,31898,6950
)
dat <- data.frame(x,y)
regfit <-  nls(y ~ lognormal(x,S0,sigma,mu) ,data =dat)


Output:

Error in nlsModel(formula, mf, start, wts) : 
        singular gradient matrix at initial parameter estimates
Warning message:
No starting values specified for some parameters.
Intializing 'S0', 'sigma', 'mu' to '1.'.
Consider specifying 'start' or using a selfStart model in: nls(y ~
lognormal(x, S0, sigma, mu), data = dat) 

Can anybody help on this topic please ?


Gunther

______________________________________________
R-help op 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.