I am trying to evaluate the purchase of a statistical tool. This will be partially used by users who are not programming (performing clinical research) and partially by programmers, so I am trying to find a good compromise between usability and automation. Of course, cost is a problem, but if I can build a solid case, we could probably buy a commercial package, so we are not limited to free options.
So far, our options are:
What else is there? What is an industry standard? What are the distinctive features I should look for? What would you recommend and why?
Ideally, we need a tool that can work on both Linux computers and Windows.
(I work in medical imaging, so we do both biostatistics and software development statistics)
Stata SPSS , . , , , . Stata , , ( , , , ).
R , . , .
R. R . , GNU.
S-PLUS R S. , S-PLUS R .
SAS - , BI . SAS , R, , , -.
SPSS, Matlab Excel.
R . , . , , , , . .
, , " SAS". SAS, . "SAS Learning Edition" (http://support.sas.com/learn/le/), Enterprise Guide, 1000 . 500 , .
S-Plus.
(S-Plus Workbench, Eclipse), - ( R, S).
Visual Numerics - .
, . : " , , , , , ", , , . Word LaTeX, ?
:
, :
: R/S-plus, Matlab/Octave ( , R, ) : Excel, R, SPSS
, R Windows , .
, . R - -, , , "image_summary", .
R python RPy.
SAS Enterprise Guide -. , Excel. . sas , - Windows.
Excel . . book book.
Wikipedia , , ( , )
As a result, we got the Matlab Statistics toolbar (mainly because we already have experience with Matlab in a team and still need a tool)
So far this does what we need to do, and it expands easily. The use will show whether the programmers really use it, but so far it looks good.