Revolutions Blog: July Roundup

[David Smith-4]

I write about R every weekday at the Revolutions blog:
 http://blog.revolutionanalytics.com
and every month I post here a summary of articles from the previous
month of particular interest to readers of r-help.

In case you missed them, here are some articles related to R from the
month of July:

A simulation in R finds the value (or disadvantage) or drawing an X,
J, Q or Z in Scrabble: http://bit.ly/qEfYNA

How to display high-quality graphics on the web using SVG output from
R: http://bit.ly/nKbFfa

A review of Paul Murrell's talk about raster image support in R:
http://bit.ly/rdNT4W

You can find other R users on LinkedIn at the R Skills page:
http://bit.ly/rrcRHL

We give thanks to the contributors to the R Project: http://bit.ly/qohlKf

Airline analyst Jeffrey Breen uses data from twitter and sentiment
analysis in R to find which airlines receive the most complaints:
http://bit.ly/r1zt5w

Marketing automation company Marketo uses Revolution R Enterprise:
http://bit.ly/pP1edA

A summary of the new features in R 2.13.1: http://bit.ly/omA9E3

An article in the New York Times about the importance of reproducible
research featured R code: http://bit.ly/posVFd

Patrick Burns simulates the S&P 500 in R to assess the validity of a
surprising forecast: http://bit.ly/psEDKA

News from Revolution Analytics in the July newsletter: http://bit.ly/psS0kK

R's GoogleVis package is used to create motion charts used on the
Lloyds Insurance website: http://bit.ly/ngLN1q

Kevin Goulding offers 10 reasons why graduate students should learn R:
http://bit.ly/p5uVtd

A video demonstration of doing a logistic regression on 1.2 billion
rows of data in 75 seconds with the RevoScaleR package:
http://bit.ly/rrSzua

GigaOm publishes an article (written by me) on 5 real-world uses of
big data, all based on R: http://bit.ly/nk6UbV

The demand for jobs involving R skills, big data, and data science is
on the rise: http://bit.ly/nb2zoQ (this post was mentioned in the New
York Times: http://bit.ly/oOaos0 )

Kickstarter uses R to visualize its successes in crowd sourcing
funding for music, design, art, game and many other kinds of projects:
http://bit.ly/oxmVgU

We congratulate Uwe Ligges on joining the R Core Group: http://bit.ly/nrgSSS

A couple of fun applications of R: reading XKCD comics, and creating
an animated elephant from complex numbers: http://bit.ly/rgWVJm

IBM Netezza sings the praises of R: http://bit.ly/pHRHBi

We profile Jeff Ryan, creator of the xts and quantmod packages:
http://bit.ly/oVQNPW

The program for useR! 2011 at the University of Warwick includes five
talks from the Revolution Analytics team: http://bit.ly/oImIkX

InformationWeek looks at Revolution R as a low-cost alternative to
SAS: http://bit.ly/peK7Ez

Steve Miller looks at applications of R for financial engineering:
http://bit.ly/mT8fm6

Other non-R-related stories included: 3-D printers
(http://bit.ly/pjLLgs ), the nostalgic online game Telehack
(http://bit.ly/og9ixS ), a grand-scale optical illusion
(http://bit.ly/qb4620 ), and optimizing Mario speed-runs
(http://bit.ly/npv8SE ).

There is a new R user group (http://bit.ly/eC5YQe ) in Buenos Aires
(http://bit.ly/mXZFrV ). Meeting times for these groups can be found
on the updated R Community Calendar at: http://bit.ly/bb3naW

If you're looking for more articles about R, you can find summaries
from previous months at http://bit.ly/9hotnN.
Join the Revolution mailing list at http://bit.ly/bsJSer to be alerted
to new articles on a monthly basis.

As always, thanks for the comments and please keep sending suggestions
to me at [hidden email] . Don't forget you can also
follow the blog using an RSS reader like Google Reader, or by
following me on Twitter (I'm @revodavid).

Cheers,
# David

--
David M Smith <[hidden email]>
VP of Marketing, Revolution Analytics  http://blog.revolutionanalytics.com
Tel: [phone] (Palo Alto, CA, USA)

______________________________________________
[hidden email] 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.

[Frank Harrell]

David, as always this is a terrific roundup.  I note in passing that the "big data" logistic function rxLogit used on the 1B observation dataset (impressive run time!) inappropriately used the t distribution for testing the coefficients in the logistic model [at least if the notation used is any clue].  It should have used the normal distribution.

Cheers,

Frank

[David Smith-4]

Thanks, Frank! I'm actually not sure what distribution it's using
there, but I'll pass this along to Sue Ranney who created the video.

Kind regards,
# David

On Tue, Aug 9, 2011 at 4:25 PM, Frank Harrell <[hidden email]> wrote:

> David, as always this is a terrific roundup.  I note in passing that the "big
> data" logistic function rxLogit used on the 1B observation dataset
> (impressive run time!) inappropriately used the t distribution for testing
> the coefficients in the logistic model [at least if the notation used is any
> clue].  It should have used the normal distribution.
>
> Cheers,
>
> Frank
>
> -----
> Frank Harrell
> Department of Biostatistics, Vanderbilt University
> --
> View this message in context: http://r.789695.n4.nabble.com/Revolutions-Blog-July-Roundup-tp3731426p3731597.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> [hidden email] 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.
>

--
David M Smith <[hidden email]>
VP of Marketing, Revolution Analytics  http://blog.revolutionanalytics.com
Tel: [phone] (Palo Alto, CA, USA)

______________________________________________
[hidden email] 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.