🚀 go-pugleaf

On Tue, 28 Dec 1999 13:41:16 GMT, nr518@aol.com wrote:
|    ** Announcing NLREG -- Nonlinear Statistical Regression Program **
|
|
|NLREG is a powerful statistical analysis program for Windows 95/98 and NT
|that performs linear and nonlinear regression analysis and curve fitting.

There is no such thing as "powerful program" working only on MS platforms.
Every powerful program should be portable to compile on other OS.

|NLREG determines the values of parameters for an equation, whose form you
|specify, that cause the equation to best fit a set of data values.  NLREG
|can handle linear, polynomial, exponential, logistic, periodic, and
|general nonlinear functions.

Every single bit of these can be made in commercial Matlab (which is
infinitely more powerful), Mathematica (which is infinitely^2 more
powerful) or any of these *free* programs (which are also infinitely more
powerful):

Scilab http://www-rocq.inria.fr/scilab/
Octave http://www.che.wisc.edu/octave/octave.html
Rlab http://www.eskimo.com/~ians/rlab.html

Any of these commercial and free programs has version running on almost
any OS in the world and especially UNIX.

|Another advantage of handing the function in true nonlinear form is that
|the minimization of the sum of squared residual values (i.e., "least
|squares") is based on the true nonlinear value rather than some linearized
|transformation.

I have to mention, that there are other cost functions except least
squares, which are also very useful in real life and science.
You should know about this.

|In addition to computing the optimal values of the parameters, NLREG can
|generate plots of the data points and the fitted equation. It can also
|plot the distribution of residual values.

This is routine with any of the software I mentioned above.

|NLREG is in use at hundreds of universities, laboratories, and government
|agencies around the world (including the U.S. Navy, Harvard, and Duke).

Thanks God, they don't use only NLREG, but mostly serious multiplatform
software.

|NLREG has been validated using the NIST statistical reference datasets;
|the results are available on the NLREG web page.

Are you joking?

|The price of NLREG is only $65 ($70 if outside the USA), which is far
|below the cost of comparable commercial regression programs.

How about Scilab, Octave or Rlab, which are free?
The basic Matlab, which is able to do much more is available at around
$100.

| And you can
|download a shareware demonstration version of NLREG to try out before you
|decide to purchase it.

The last versions of free programs I mentioned are available for download
at any moment. Feel free to download them and possibly to make your
program open source and free. Learn more about other players in the field.

Good luck!

--JS

PS. I am posting this to all newsgroups you posted your "promo", so that
people know the real situation and don't pay money for your product, as
much better products are available for free.