Date: Thu, 14 Jan 2010 12:13:35 -0600
Reply-To: "Steve Simon, P.Mean Consulting" <net@pmean.com>
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: "Steve Simon, P.Mean Consulting" <net@pmean.com>
Subject: Re: Updated comparison table for SAS-SPSS Add-ons and R Functions
In-Reply-To: <8C5F8DF18B90FA43BB9B356227F812D5016381A6@KFSVS6.utk.tennessee.edu>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Muenchen, Robert A (Bob) wrote:
> I have substantially expanded the table that compares SAS and SPSS
> add-on modules to somewhat equivalent R packages. This new version is
> at:
> http://r4stats.com/add-on-modules
> and I would very much appreciate any feedback you might have on it.
Very nice site. I would suggest that you refer to
http://www.spss.com/software/product-name-guide/
for the names of the SPSS products. Typically, where you say "IBM SPSS",
it should probably read "PASW". It might be worthwhile to always list
both the old and new names side by side because some of us are still
confused by all the name changes. So your first row might read
* PASW Advanced Statistics/SPSS Advanced Statistics
and the row on classification/cluster analysis might read
* PASW Classification/Clementine Classification Module
The section on data mining is a bit confusing, which is largely because
data mining is such a broad area. Also, classification and clustering
are not at all similar, so the row on this topic should be split. I'd
break it up into supervised learning (classification) and include things
like neural nets, support vector machines, discriminant analysis. The
other broad category in data mining is unsupervised learning
(clustering/segmentation analysis) and it might include things like
kmeans clustering, hierarchical clustering, and model based clustering.
You should add rows for
* Bayesian data analysis
* Generalized linear models
* Item Response Theory
* Logistic regression
* Nonlinear regression
* ROC curves
* Survival data
The section on power analysis should be better titled as "Power and
sample size calculations"
The topic "Advanced Models" is too vague and too broad. I would use some
of the terms mentioned above instead. If you do keep "Advanced Models" I
would define it somehow (non-linear models? generalized linear models?)
Similarly, the term "Regression models" is vague. I assume that you mean
multiple linear regression models or general linear models.
There are more R packages for genetics than just Bioconductor.
These comments are all minor. The list, as it stands, is excellent. You
are welcome to take or ignore any or all of these comments.
--
Steve Simon, Standard Disclaimer
"The first three steps in a descriptive
data analysis, with examples in PASW/SPSS"
Thursday, January 21, 2010, 11am-noon, CST.
Free to all! Details at www.pmean.com/webinars
=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
