R help - Jan 2010 - term.formula error when updating an nls object

Hi,

I'm getting an error that I don't understand when updating an nls
object.  Here is a toy example.

dd <- structure(list(Contrast = c(0.00376, 0.03759, 0.12782, 0.25564,
0.50376, 1), Response = c(0.29915, 6.13248, 29.01709, 30.0641,
29.46581, 27.67094)), .Names = c("Contrast", "Response"),
class =
"data.frame", row.names = c(NA,
-6L))

m1 <- nls(Response ~
			Rm * Contrast^ex/(Contrast^ex + sig^ex),
			data = dd,
			start = list(Rm = 30, sig = 0.05, ex = 3))

m2 <- update(m1, . ~
			Rm * Contrast^ex/(Contrast^fx + sig^fx),
			start = list(Rm = 30, sig = 0.05, ex = 3,
			fx = 3.1))
Error in terms.formula(tmp, simplify = TRUE) : invalid power in formula

but there is nothing wrong with fitting the second model directly
with nls

m2a	<- nls(Response ~
			Rm * Contrast^ex/(Contrast^fx + sig^fx),
			data = dd,
			start = list(Rm = 30, sig = 0.05, ex = 3,
			fx = 3.1))


nor with fitting the model with the data transformed (though it is
not necessarily the way I would like to fit the model in this
case).

m2b <- update(m1, log(.) ~ log(.))
m3 <- update(m2b, . ~
	log(Rm * Contrast^ex/(Contrast^fx + sig^fx)),
	start = list(Rm = 30, sig = 0.05, ex = 3,
			fx = 3.1))

sessionInfo()
R version 2.10.1 Patched (2010-01-25 r51051)
i386-apple-darwin9.8.0

locale:
[1] en_US.UTF-8/en_US.UTF-8/C/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods
[7] base

Thanks, in advance, for any help.

Ken

-- 
Ken Knoblauch
Inserm U846
Stem-cell and Brain Research Institute
Department of Integrative Neurosciences
18 avenue du Doyen L?pine
69500 Bron
France
tel: +33 (0)4 72 91 34 77
fax: +33 (0)4 72 91 34 61
portable: +33 (0)6 84 10 64 10
http://www.sbri.fr/members/kenneth-knoblauch.html

Ken,

You just need to wrap the rhs of your formula in I() to
get around update()'s parsing of terms.

  m2 <- update(m1, . ~
              I(Rm * Contrast^ex/(Contrast^fx + sig^fx)),
              start = list(Rm = 30, sig = 0.05, ex = 3,
              fx = 3.1))

  -Peter Ehlers

Ken Knoblauch wrote:
> Hi,
> 
> I'm getting an error that I don't understand when updating an nls
> object.  Here is a toy example.
> 
> dd <- structure(list(Contrast = c(0.00376, 0.03759, 0.12782, 0.25564,
> 0.50376, 1), Response = c(0.29915, 6.13248, 29.01709, 30.0641,
> 29.46581, 27.67094)), .Names = c("Contrast",
"Response"), class =
> "data.frame", row.names = c(NA,
> -6L))
> 
> m1 <- nls(Response ~
>             Rm * Contrast^ex/(Contrast^ex + sig^ex),
>             data = dd,
>             start = list(Rm = 30, sig = 0.05, ex = 3))
> 
> m2 <- update(m1, . ~
>             Rm * Contrast^ex/(Contrast^fx + sig^fx),
>             start = list(Rm = 30, sig = 0.05, ex = 3,
>             fx = 3.1))
> Error in terms.formula(tmp, simplify = TRUE) : invalid power in formula
> 
> but there is nothing wrong with fitting the second model directly
> with nls
> 
> m2a    <- nls(Response ~
>             Rm * Contrast^ex/(Contrast^fx + sig^fx),
>             data = dd,
>             start = list(Rm = 30, sig = 0.05, ex = 3,
>             fx = 3.1))
> 
> 
> nor with fitting the model with the data transformed (though it is
> not necessarily the way I would like to fit the model in this
> case).
> 
> m2b <- update(m1, log(.) ~ log(.))
> m3 <- update(m2b, . ~
>     log(Rm * Contrast^ex/(Contrast^fx + sig^fx)),
>     start = list(Rm = 30, sig = 0.05, ex = 3,
>             fx = 3.1))
> 
> sessionInfo()
> R version 2.10.1 Patched (2010-01-25 r51051)
> i386-apple-darwin9.8.0
> 
> locale:
> [1] en_US.UTF-8/en_US.UTF-8/C/C/en_US.UTF-8/en_US.UTF-8
> 
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods
> [7] base
> 
> Thanks, in advance, for any help.
> 
> Ken
> 
-- 
Peter Ehlers
University of Calgary