[R] where are my pspline knots?

David Winsemius dwinsemius at comcast.net
Wed Nov 17 20:39:10 CET 2010


On Nov 17, 2010, at 1:05 PM, Federico Calboli wrote:

> Hi All,
>
> I am trying to figure out how to get the position of the knots in a  
> pspline used in a cox model.

As far as I understand it, the term "knot" should be used with natural  
splines, but not for penalized smoothing splines. See p 124 of  
Therneau and Gramsch for better description and illustrations. If you  
want to see the weighting of a particular pspline then this example  
may help:

nn=rnorm(20)
matrix(pspline(nn), nrow=20)[order(nn), ]
# sorts the spline basis weights so the overlap is "visible"

-- 
David.

>
> my.model = coxph(Surv(agein, ageout, status) ~ pspline(x), mydata) #  
> x being continuous
>
> How do I find out where the knot of the spline are? I would like to  
> know to figure out how many cases are there between each knot.
>
> Best,
>
> Federico
>
> --
> Federico C. F. Calboli
> Department of Epidemiology and Biostatistics
> Imperial College, St. Mary's Campus
> Norfolk Place, London W2 1PG
>
> Tel +44 (0)20 75941602   Fax +44 (0)20 75943193
>
> f.calboli [.a.t] imperial.ac.uk
> f.calboli [.a.t] gmail.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.

David Winsemius, MD
West Hartford, CT



More information about the R-help mailing list