[R] variable bandwidths in R

[Bert Gunter]

Inline.

On Sun, Jul 28, 2013 at 10:38 AM, Rui Barradas <ruipbarradas at sapo.pt> wrote:
> Hello,
>
> You should Cc the list, the odds of getting more and better answers is
> greater.
> I don't believe what you want is statistically sound, why more than one
> bandwidth? Anyway, if density() doesn't do what you need, you can try to
> look for similar functions in other packages. Try the following.
>
> library(sos)
>
> findFn('kernel density estimation')
>
>
> There are several hits with 'kde' in the name of the function. But I doubt
> they implement multiple bandwidths per call.

I agree. Trying adding "adaptive" to your search (e.g. "adaptive
smoothing", "adaptive density estimation" or whatever.

-- Bert


>
> Rui Barradas
>
> Em 28-07-2013 16:11, Ms khulood aljehani escreveu:
>>
>>
>> Hi
>> Thank You for your help
>>
>> I tried this way, bw argument allowed to one value
>> I want more than one value, and this values change as the observation in
>> the original vector change
>>
>> Thank You
>>
>>> Date: Sun, 28 Jul 2013 10:33:35 +0100
>>> From: ruipbarradas at sapo.pt
>>> To: aljehani-k at hotmail.com
>>> CC: r-help at stat.math.ethz.ch
>>> Subject: Re: [R] variable bandwidths  in R
>>>
>>> Hello,
>>>
>>> Try function ?density, argument bw, in package stats.
>>>
>>> Hope this helps,
>>>
>>> Rui Barradas
>>>
>>> Em 28-07-2013 04:18, Ms khulood aljehani escreveu:
>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>> HelloI want to know how can
>>>> implement variable bandwidths  for kernel
>>>> density estimation in R.
>>>>
>>>> What the packages that
>>>> I need to use? And what the command?
>>>>
>>>>
>>>>
>>>> Thank You Khulood H.
>>>>
>>>>
>>>>
>>>>
>>>>         [[alternative HTML version deleted]]
>>>>
>>>> ______________________________________________
>>>> 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.
>>>>
>>
>>
>
> ______________________________________________
> 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