[R] Question about NLS model

[Bert Gunter]

Liang:

In nonlinear models especially (and more generally, also), "small" p
values are not reliable indicators of whether a fit is or is
not"good." I would strongly suggest that you consult with your local
statistician -- this is a (complicated, as it depends on the meaning
of "good") statistical discussion that does not belong here.

-- Bert

On Thu, Feb 7, 2013 at 8:15 AM, Liu, Liang <gocrag at gmail.com> wrote:
> Thanks, Ellison. Another question is if this p-value is a good parameter to
> test if the fitting is good, as you this test is only for the null that the
> coefficient is 0 (a is 0 in y=exp(a*x), right?)?
>
>
> On Thu, Feb 7, 2013 at 10:48 AM, S Ellison <S.Ellison at lgcgroup.com> wrote:
>
>>
>>
>> > After applying the NLS for a model like y=exp(a*x), and I get
>> > a result showing the summary as:
>> > Estimate Std. Error t value Pr(>|t|)
>> > 2.6720     1.4758   1.811   0.3212
>> >
>> > My question is what this t-statistics tests? And what's the
>> > meaning of Pr?
>> t is (estimate/std.err) and can be used to test the null that the
>> coefficient is 0.
>> Pr is the corresponding p-value; the fact that it says "> |t|" indicates
>> the number of tails.
>>
>> S
>>
>> *******************************************************************
>> This email and any attachments are confidential. Any u...{{dropped:12}}
>
> ______________________________________________
> 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