« How do you know if your model is going to work? Part 4: Cross-validation techniques | Main | The R Consortium Gears Up For Business »

September 23, 2015

Comments

Feed You can follow this conversation by subscribing to the comment feed for this post.

For all those on the bleeding edge, you're going to get some (or most/all) of these for "free" in the next ggplot2 release with the forthcoming ggalt package: https://github.com/hrbrmstr/ggalt

Right now it has a 'geom_xspline()' but once I get some cycles the others will be added (or y'all can follow the idiom in geom_xspline() and submit a PR :-)

What is the preferred approach to interpolate points in three dimensional space in order to create a smooth estimated plane/wireframe out of noisy data sample? Is there an elegant way to get rid of outliers in order to avoid local distortions in the interpolated plane shape and allow for smooth curvature in the result?

Good summary! I just want to mention that smoothing can have detrimental effects if you want to quantify (predict) some response value on the smoothed values, especially when using running means.
See our paper on that:
http://www.clinchem.org/content/61/2/379.abstract

Cheers,
Andrej

The comments to this entry are closed.

Search Revolutions Blog




Got comments or suggestions for the blog editor?
Email David Smith.
Follow revodavid on Twitter Follow David on Twitter: @revodavid
Get this blog via email with Blogtrottr
‚Äč