[R] Statistical / data mining methods in R and not in SAS?

[Bert Gunter]

David's reply is far more comprehensive, but it may be worth adding
that new "data mining" packages are being added almost daily to R
software repositories (CRAN, github, etc.), so that anything one would
say about this becomes almost instantly outdated. e.g. from a post 4
days ago here from Nan Xiao:

-----

"- I am pleased to announce that the R package OHPL is now available on
CRAN (https://CRAN.R-project.org/package=OHPL).

The package implements the ordered homogeneity pursuit lasso (OHPL)
algorithm for group variable selection proposed in Lin et al. (2017)
<doi:10.1016/j.chemolab.2017.07.004>. The OHPL method exploits the
homogeneity structure in high-dimensional data and enjoys the grouping
effect to select groups of important variables automatically. This
feature makes it particularly useful for high-dimensional datasets with
strongly correlated variables, such as spectroscopic data.

For more information, please see https://OHPL.io."
----
You certainly wouldn't find this in SAS software!

Cheers,
Bert


Bert Gunter

"The trouble with having an open mind is that people keep coming along
and sticking things into it."
-- Opus (aka Berkeley Breathed in his "Bloom County" comic strip )


On Tue, Aug 15, 2017 at 6:34 PM, David Winsemius <dwinsemius at comcast.net> wrote:
>
>> On Aug 14, 2017, at 12:22 PM, fs <mail at friedrich-schuster.de> wrote:
>>
>> Hi, and sorry for asking such an unspecific question.
>>
>> Does anybody know of statistical / data mining methods that are available in R
>> that are not in SAS ? With SAS I mean the SAS System Version 9.4 and SAS
>> Enterprise Miner. I don't expect a complete list, just two or three examples
>> or hints where and what to look for.
>>
>> I found some older comparisons, and the R methods mentioned there (GLMET, RF,
>> ADABoost) are now supported by SAS (at least to some degree).
>>
>> And there exists a (massive) list of available models for the caret package
>> here: https://rdrr.io/cran/caret/man/models.html, but it's hard to analyze the
>> complete list.
>>
>> (I'm trying to answer a question of a colleague).
>
> It wasn't clear whether it was statistical procedures themselves or connections to back-end data and machine learning packages might be the metric of comparison. I also thought the question would have been better posted on a SAS website, since the CRAN Task Views provide an even more complete listing and most of us are not current users of the SAS Enterprise Miner Suite. The SAS users might have a better notion of their capacities and limitations.
>
> You might start by comparing:
>
> 1) https://www.sas.com/content/dam/SAS/en_us/doc/factsheet/sas-enterprise-miner-101369.pdf
>
> ... although that did not appear to be a comprehensive listing of available model types.
>
> With:
>
> 2a) https://cran.r-project.org/web/views/MachineLearning.html
> 2b) https://cran.r-project.org/web/views/Bayesian.html
> 2c) https://cran.r-project.org/web/views/ExtremeValue.html
> 2d) https://cran.r-project.org/web/views/FunctionalData.html
> 2e) https://cran.r-project.org/web/views/Robust.html
> 2f) https://cran.r-project.org/web/views/SpatioTemporal.html
> 2g) https://cran.r-project.org/web/views/Spatial.html
>
> Left out several Task Views since they might be probably too "ordinary", but you should look at all of them:
> https://cran.r-project.org/web/views/
>
>
> Other websites possibly outlining areas of possible difference:
>
> https://tensorflow.rstudio.com/
>
> https://blog.rstudio.com/2016/09/27/sparklyr-r-interface-for-apache-spark/
>
> https://spark.rstudio.com/reference/sparklyr/latest/ml_multilayer_perceptron.html
>
> https://communities.sas.com/t5/SAS-IML-Software-and-Matrix/TensorFlow-MNIST/td-p/318708
>
> https://thomaswdinsmore.com/2017/04/05/sas-peddles-open-source-fud/
>
>
>
> --
> David Winsemius
> Alameda, CA, USA
>
> 'Any technology distinguishable from magic is insufficiently advanced.'   -Gehm's Corollary to Clarke's Third Law
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.