[R] loess smoothing

[Greg Snow]

The loess.demo function in the TeachingDemos package helps visualize what is happening with the loess algorithm, it may answer some of your questions.

Simply, the span can be greater than 1, a span of 3/4 mean use the 3/4 of the points closest to where you are trying to predict, a span of 1 means use all the points (but their weights will change for where you are predicting), spans greater than 1 still use all the points, but the weights become more similar to each other, as span approaches Inf, the loess curve approaches a straight line.

Hope this helps,

-- 
Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org
801.408.8111


> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of rkevinburton at charter.net
> Sent: Thursday, November 19, 2009 4:03 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] loess smoothing
> 
> Hello,
> 
> In reading the loess description I see:
> 
>  span: the parameter alpha which controls the degree of smoothing.
> 
> The default seems to be 0.75. Would it be possible to expand on this
> decription so I can avoid trail and error? Can I increase this pass
> 'span' > 1? Qualitatively to what degree changing this value affects
> the smoothing of the data?
> 
> Thank you.
> 
> Kevin
> 
> ______________________________________________
> 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.