Simon
I wonder whether I can take advantage of this thread and ask you another
related question. Now, I want to get the 95%CI of the fit and their
derivatives as well. For the original fitted curves, It is straightforward
as the option "type=terms" can be used to get the CI for the fixed effect.
N
Hi, Simon
Thank you for your explanation! I followed the instructions and
successfully get the predicted values with both fixed and random effects
incorporated: pred.new=predict.gam(gamm1$gam,newdata,type="response").
Also, what I meant to say was "plot(gamm1$gam, pages=1)" for left and right
fig
>
> gamObj=gam(brainVolume~ s(correctedAge) + s(subjIndexF, bs="re") +
> s(subjIndexF, correctedAge, bs="re"), method="REML", data=mydata),
> where subjIndexF is a factor for each subject. I was thrown an error
> saying "more coefficients than data".
>
--- I'm not sure exactly how many scans a
If 'subjIndexF' is a factor for subject, then s(subjIndexF, bs="re")
will produce a random effect for subject. i.e. each subject will be
given its own random intercept term, which is a way that repeated
measures data like this are often handled.
The reason for the s(subjIndexF, bs="re") syntax
> On Mar 30, 2017, at 6:56 AM, Leon Lee wrote:
>
> David
>
> Thank you for your reply. I apologize if I posted in the wrong forum, as I
> really couldn't decide which forum is the best place for my question and I
> saw similar questions asked before in this forum.
>
> I agree that a sample
David
Thank you for your reply. I apologize if I posted in the wrong forum, as I
really couldn't decide which forum is the best place for my question and I
saw similar questions asked before in this forum.
I agree that a sample of ~30 subjects (70 scans in total), the model can be
too complicated
> On Mar 28, 2017, at 9:32 AM, Leon Lee wrote:
>
> Hi, R experts
>
> I am new to R & GAM toolbox and would like to get inputs from you all on my
> models. The question I have is as follows:
> I have 30 subjects with each subject being scanned from one to three times
> in the first year of life.
Hi, R experts
I am new to R & GAM toolbox and would like to get inputs from you all on my
models. The question I have is as follows:
I have 30 subjects with each subject being scanned from one to three times
in the first year of life. The brain volume from each scan was measured.
The scan time was
8 matches
Mail list logo