[R] R seven years ago

Fri Oct 10 11:21:31 CEST 2008

Not to detract from John's very interesting work, but
there is a problem with citations as a measure of
penetration.  When R totally succeeds, there will be
no citations.  How many citations are there for Excel?
However, for the moment, citations are probably a
pretty good measure.

Using traffic on R-help is even more problematic in
this regard.  Each question sent to R-help is clearly a
failure (of documentation) rather than a success.  Plus,
unlike citations, there is a limit to the capacity of a mailing
list -- exponential growth in messages on a single list is
clearly unsustainable.  To look at such statistics it would
make sense to sum over all the R mailing lists.

Tangential: In the early days of S-news it was apparent
that traffic was a proxy not for total users but for new users.

Clarification: Saying that a question to R-help is a failure
of documentation is neither denigrating R documentation nor
letting questioners off the hook when the answer to their
question is clearly and prominently documented.  I'm saying
that for whatever reason the questioner found it less costly
to post a question than to find the answer in the documentation.
Cost functions vary.

Patrick Burns
patrick at burns-stat.com
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of S Poetry and "A Guide for the Unwilling S User")

John Maindonald wrote:
> So what is the answer to the question: "Can success continue"?
>
> I suspect that R is now so firmly entrenched that it will
> inevitably continue, in one or other incarnation, for a long
> time to come.  The negative factors that John Fox lists
> will surely, in time, make some changes inevitable.  Will
> these come from force of circumstance rather than from
> conscious planning?
>
> In an August 12 message I posted details of R citation rates that
> I had gleaned, following a lead from Simon Blomberg, from Web
> of Science.  This, or some such measure, seems to me important
> as giving a handle on the penetration of R into statistical
> application areas.
>
> The numbers I obtained [I&G = Ihaka & Gentleman 1996; RSTAT is
> the citation suggested by citation()] were:
>
> I&G: 1998=4,
>           1999=15,
>            2000=17,
>            2001=39,
>            2002=119,
>            2003=276
> RSTAT+I&G: 2004:68+455 = 523
>                         2005:433+512 = 945
>                         2006:1049+426 = 1475
>                         2007:1605+410 = 2015
>                         2008, (to ~Aug10):1389+255 = 1644
>
> cit <- c("1998" = 4, "1999" = 15, "2000" = 17, "2001" = 39, "2002" =  
> 119,
>     "2003" = 276, "2004" = 523,"2005" = 945,"2006" = 1475, "2007" =  
> 2015,
>     "2008"=1644)
>
> These will not be all that accurate; there will be omissions
> and duplications.
>
> Growth is close to exponential.
>
> John Maindonald             email: john.maindonald at anu.edu.au
> phone : +61 2 (6125)3473    fax  : +61 2(6125)5549
> Centre for Mathematics & Its Applications, Room 1194,
> John Dedman Mathematical Sciences Building (Building 27)
> Australian National University, Canberra ACT 0200.
>
>
> On 09/10/2008, at 9:00 PM, r-help-request at r-project.org wrote:
>
>   
>> From: Peter Dalgaard <P.Dalgaard at biostat.ku.dk>
>> Date: 9 October 2008 5:42:19 AM
>> To: ted.harding at manchester.ac.uk
>> Cc: "r-help at R-project.org" <r-help at r-project.org>
>> Subject: Re: [R] R seven years ago
>>
>>
>> (Ted Harding) wrote:
>>     
>>> On 08-Oct-08 18:00:27, Liviu Andronic wrote:
>>>
>>>       
>>>> Hello everyone,
>>>>
>>>> As some may know, today Google unveiled its 2001 search index [1]. I
>>>> was curious to see how was R like at that time, and was not
>>>> disappointed. Compared to today's main page [2], seven years ago the
>>>> page looked [3] a bit rudimentary, especially the graphic. (It is  
>>>> wort
>>>> noting that structurally the pages are very similar.) What  
>>>> definitely
>>>> changed is the `Contributed packages' section. Then R featured 29
>>>> contributed packages [4], while now it features 1500+ [5]. It was
>>>> surprising to realize the growth of R during the past seven years.
>>>>
>>>> Regards,
>>>> Liviu
>>>>
>>>> [1] http://www.google.com/search2001.html
>>>> [2] http://www.r-project.org/
>>>> [3] http://web.archive.org/web/20010722202756/www.r-project.org/
>>>> [4]
>>>> http://web.archive.org/web/20010525004023/cran.r-project.org/bin/macos/c
>>>> ontrib/src/
>>>> [5] http://cran.at.r-project.org/web/packages/
>>>>
>>>>         
>>> Many thanks for this, Liviu! One might also compare the mailing list
>>> usage:
>>>
>>> [R-help 1997]:   484 messages
>>> [R-help 2001]:  4309 messages
>>> [R-help 2007]: 26250
>>>               1721+1909+2196+2145+2210+2309+
>>>               2142+2246+2028+2711+2602+2031
>>>
>>> So we now get more posts in a week than we did in the whole of 1997!
>>>
>>>
>>>       
>> Those not present at the useR in Dortmund might want to skim John  
>> Fox's talk
>>
>> http://www.statistik.uni-dortmund.de/useR-2008/slides/Fox.pdf
>>
>> (Actually, he did something at the end to avoid ending on a negative
>> note. Flipped back to one of the increasing graphs, I suppose.)
>>
>> -- 
>>   O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
>>  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
>> (*) \(*) -- University of Copenhagen   Denmark      Ph:  (+45)  
>> 35327918
>> ~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)              FAX: (+45)  
>> 35327907
>>     
>
>
> 	[[alternative HTML version deleted]]
>
>   
> ------------------------------------------------------------------------
>
> ______________________________________________
> 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.
>