[R] mgcv package, problems with NAs in gam

[Bert Gunter]

Grace:

Confession: I loved that error message!  -- and it seems pretty clear to me.

What does "to no avail" mean -- in particular, what happened when you
changed your NA's to 0? Presumably you did not get the same error
message, again, but something else, right? What else?

Modulo the above vagueness, I would guess you're stuck -- you can't do
what you'd like with your data. If so, John Tukey's remark from
decades ago seems apropos:

"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."
American Statistician 40 (1986)

But if you post with greater clarity -- or get a response from someone
with a greater brain -- maybe there's hope.

Cheers,
Bert


On Fri, Aug 24, 2012 at 2:36 PM, grace <sololorox at hotmail.com> wrote:
> Hi there,
>
> I'm using presence-absence data in a gam (i.e. 0 or 1 as values)
> I am trying to run a gam with 'dummy covariates' i.e. 1~1
> unfortunately my model:
> *
> model<-gam(1~1, data=bats, family=negbin)*
>
> keeps putting out:
>
> *
> Error in gam(1 ~ 1, data = bats, family = negbin) :
>   Not enough (non-NA) data to do anything meaningful*
>
> Is there a specific reason it would do this? I have tried using various
> actions on NAs, na.pass etc, as well as asking it to turn all NAs to 0 but
> to no avail.
>
> I would post the data here but its rather long, basically 28x104 matrix of
> 0/1 with headers 'v1:v28' .The summary for the data comes up fine, it's just
> the model that isn't working.
> However if I run using:
>
> *model<-gam(v1~v2, data=bats, family=negbin)
> *
>
> it tends to work.
>
> Any help is seriously appreciated as I have a deadline and have been trying
> this for days,
>
> Thanks!
>
>
>
> --
> View this message in context: http://r.789695.n4.nabble.com/mgcv-package-problems-with-NAs-in-gam-tp4641253.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at 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.



-- 

Bert Gunter
Genentech Nonclinical Biostatistics

Internal Contact Info:
Phone: 467-7374
Website:
http://pharmadevelopment.roche.com/index/pdb/pdb-functional-groups/pdb-biostatistics/pdb-ncb-home.htm