bug in logLik.nls (PR#2295)

lutz@stat.math.ethz.ch lutz@stat.math.ethz.ch
Fri, 15 Nov 2002 13:12:09 +0100 (MET)


logLik.nls does not count the df's correct. I get df=1 although I
fit a probit-model with 3 parameters.

Example:
x <- c(-2.3, -2.0, -1.3, -1.0, -0.7, -0.3, 0.0, 0.3)
y <- c(80, 80, 54, 43, 24, 18, 12, 12)

fit.nls <- nls(y ~ diff * pnorm(beta * (x - alpha)),
                   start=c(alpha=-1, beta=-1, diff=100))

logLik.nls(fit.nls)
# `log Lik.' -21.43369 (df=1)


Sincerely yours
Roman Lutz

--please do not edit the information below--

Version:
 platform = i686-pc-linux-gnu
 arch = i686
 os = linux-gnu
 system = i686, linux-gnu
 status = 
 major = 1
 minor = 6.1
 year = 2002
 month = 11
 day = 01
 language = R

Search Path:
 .GlobalEnv, package:mva, package:lattice, package:grid, package:nlme, package:nls, package:ctest, package:SfS, Autoloads, package:base

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-devel mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-devel-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._