README
======

Thank you for acquiring a copy of stats.  I hope you enjoy it. If you
do find this program useful, send me a note telling me so.  Also,
please send me any suggestions you have as to how to make this package
better. The first section has the directions for installation.  The
second rambles on about copyright stuff.

Mark

--Mark Claypool----Worcester Polytechnic Institute----claypool@cs.wpi.edu-- 

FILES
=====
Changes       Some modifications to the stats program.
Makefile      To build stats.c.
README        This file.
gnuplot.help  A helpfile for using gnuplot for graphing stats.c output.
stats.c       The source code for stats.
stats.man     Some rudimentary man pages.

INSTALLATION
============
To install stats:

1) Unpack the makefile (Makefile), man page (stats.man) and source
code (stats.c) in a separate directory.

2) Edit the makefile to your liking.  In particular, change the
destination variable DEST. If you are using a compiler other than gcc,
the CFLAGS will change.

3) Type "make". It should make the program "stats" in the current directory. 

4) Type "make install".  It will copy "stats" and "stats.man" to the 
destination directory.

5) Enjoy!

-----------------------------------------------------------------------------

COPYRIGHT NOTICE
================
This software, stats, is copyright 1994, 2006 by Mark Claypool.

Permission to use, copy, and distribute stats in its entirety, for
non-commercial purposes, is hereby granted, provided that the
copyright notice appear in all copies.

The software may be modified for your own purposes, but modified
versions may NOT be distributed without prior consent of the author.

This software is provided 'as-is', without any express or implied
warranty.  In no event will the author be held liable for any damages
arising from the use of this software.

If you would like to do something with stats that this copyright
prohibits (such as distributing it with a commercial product, 
using portions of the source in some other program, etc.), please
contact the author (preferably via email).  Arrangements can
probably be worked out.

The author may be contacted via email at claypool@cs.wpi.edu.

-----------------------------------------

NOTES on Exponential Regression

To obtain a best-fit exponential curve of the form

    y = K r^x 

Find the best-fit linear regression for the data (x, log y)

   slope = b
   intercept = a

The desired coefficients A and r are then:

        r = 10^b
        K = 10^a

Note, to take the log of a number, e.g. log base 10,
do:

   ln(number) / ln(10)

