Caveat: Both of the following claims are subject to verification by true experts, which I am not. But I believe:
1. If all values being smoothed are positive, then the smoother must be also. If there are negative values, this is no longer true, and your question needs much more detail to get an answer. 2. Just restrict the (pointwise) CI's to your desired range if they fall outside of it. This assumes that values outside the range cannot occur. If that assumption is wrong, again you will need to provide much greater detail. -- Bert On Thu, Feb 2, 2012 at 10:09 AM, ioanna <ii54...@msn.com> wrote: > Is it possible to apply a kernel smoothing regression whose estimator or > indeed the confidence intervals cannot take negative values or values > greater than 1? > > Best regards, > Ioanna > > -- > View this message in context: > http://r.789695.n4.nabble.com/kernel-smoothing-of-disease-rates-at-locations-tp799701p4352286.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@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 ______________________________________________ R-help@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.