Full_Name: Tadashi Kadowaki Version: 2.4.0 OS: Redhat Linux 9 Submission from: (NULL) (58.12.166.67) Doesn't nls function support subset? It seems not to work. And, there are no information in the online help. Has it sunk into oblivion?
nls function does not use subset argument (PR#9290)
4 messages · tadakado at gmail.com, Brian Ripley, Peter Dalgaard +1 more
This is not the place to ask a question: do read the FAQ. ?nls shows that nls does have a 'subset' argument, and it does work. Compare
?nls x <- 1:10 y <- 2*x + 3 # perfect fit yeps <- y + rnorm(length(y), sd = 0.01) # added noise nls(yeps ~ a + b*x, start = list(a = 0.12345, b = 0.54321),
+ trace = TRUE)
1360.779 : 0.12345 0.54321
0.000778241 : 3.002946 1.999563
0.000778241 : 3.002946 1.999563
Nonlinear regression model
model: yeps ~ a + b * x
data: parent.frame()
a b
3.002946 1.999563
residual sum-of-squares: 0.000778241
nls(yeps ~ a + b*x, start = list(a = 0.12345, b = 0.54321),
+ trace = TRUE, subset=1:9)
1056.760 : 0.12345 0.54321
0.0007055261 : 3.000838 2.000138
0.0007055261 : 3.000838 2.000138
Nonlinear regression model
model: yeps ~ a + b * x
data: parent.frame()
a b
3.000838 2.000138
residual sum-of-squares: 0.0007055261
I find your comments baffling: please provide a reproducible example of
your claims.
On Wed, 11 Oct 2006, tadakado at gmail.com wrote:
Full_Name: Tadashi Kadowaki Version: 2.4.0 OS: Redhat Linux 9 Submission from: (NULL) (58.12.166.67) Doesn't nls function support subset? It seems not to work. And, there are no information in the online help. Has it sunk into oblivion?
______________________________________________ R-devel at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-devel
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
tadakado at gmail.com writes:
Full_Name: Tadashi Kadowaki Version: 2.4.0 OS: Redhat Linux 9 Submission from: (NULL) (58.12.166.67) Doesn't nls function support subset? It seems not to work. And, there are no information in the online help. Has it sunk into oblivion?
Whatever gave you those ideas? Yes, nls supports subset. Yes, it does seem to work. Yes, it is documented in the online help. No, it has not sunk into anything.
nls(density ~ SSlogis(log(conc), Asym, xmid, scal), DNase, subset=Run==1)
Nonlinear regression model
model: density ~ SSlogis(log(conc), Asym, xmid, scal)
data: DNase
Asym xmid scal
2.345180 1.483090 1.041455
residual sum-of-squares: 0.004789569
O__ ---- Peter Dalgaard ?ster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907
I am sorry, it was my program's bug. Yes, subset works! Yes, nls works correctly! I didn't pay enough attention to NAs. NA threw off start value estimation in my program. So, I got different results when I filtered NAs beforehand and filtered by subset. I also confused because subset does not appear in the code of the nls function. Then, I reached a wrong conclusion. Thank you very much for your time. Tadashi Kadowaki 11 Oct 2006 11:55:56 +0200, Peter Dalgaard <p.dalgaard at biostat.ku.dk>:
tadakado at gmail.com writes:
Full_Name: Tadashi Kadowaki Version: 2.4.0 OS: Redhat Linux 9 Submission from: (NULL) (58.12.166.67) Doesn't nls function support subset? It seems not to work. And, there are no information in the online help. Has it sunk into oblivion?
Whatever gave you those ideas? Yes, nls supports subset. Yes, it does seem to work. Yes, it is documented in the online help. No, it has not sunk into anything.
nls(density ~ SSlogis(log(conc), Asym, xmid, scal), DNase, subset=Run==1)
Nonlinear regression model model: density ~ SSlogis(log(conc), Asym, xmid, scal) data: DNase Asym xmid scal 2.345180 1.483090 1.041455 residual sum-of-squares: 0.004789569 -- O__ ---- Peter Dalgaard ?ster Farimagsgade 5, Entr.B c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907