In article <8lalui$655$[EMAIL PROTECTED]>, <[EMAIL PROTECTED]> wrote:
>I am looking for way to automate numerical analysis.
Numerical analysis is an art, not a science. However,
you want to automate not numerical analysis, but the
implementation of a particular sequence of algorithms.
Your package must have all the algorithms, or you will
have to move intermediate results.
In the particular problem you have, one of the numerical
analysis packages, or Splus or the equivalent R, will do
what you have asked. SAS is not up to that level.
There is no problem in using the ones I have cited on
Unix; we are doing this. I am not in systems; do not
ask me how.
Specifically I
>want a program to take as input a time series from a flat text file,
>some settings on what analysis to perform, then use, for example,
>lagrange polynomial interpolation to produce a polynomial regression
>equation. From there I could write a program to graph predicited
>results. So far I've gone through applications, source libraries, and
>just today spoke with a sales rep from SAS for 30 minutes. However I
>may be making this more complex then it really is. Has anyone come
>across a similar problem or have advice on how to do this? SAS seems
>to be the only program that is flexible enough to run on unix and be
>automated. I would prefer a more simplistic approach as there is _a
>lot_ of overhead in starting to use SAS. Any help or suggestions would
>be appreciated!
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
