[19219] in s-news-athena

home help back first fref pref prev next nref lref last post

Re: [S] Results: weighted histogram, AND bootstrap code

daemon@ATHENA.MIT.EDU (Tim Hesterberg)
Tue Sep 14 11:09:40 1999

Date: Tue, 14 Sep 1999 08:02:48 -0700 (PDT)
Message-Id: <199909141502.IAA11396@quake.statsci.com>
From: Tim Hesterberg <timh@statsci.com>
To: s-news@wubios.wustl.edu
Cc: christian.hoffmann@lagonda.wsl.ch
In-Reply-To: <3.0.5.32.19990914143247.009fbb50@mail.wsl.ch> (message from
	Christian Hoffmann on Tue, 14 Sep 1999 14:32:47 +0200)
Reply-To: timh@statsci.com (Tim Hesterberg)


Christian Hoffman summarized responses he received regarding
weighted histograms, including:

>2) Tim Hesterberg <timh@statsci.com>, MathSoft wrote: "I have code that does
>weighted histograms, calling a weighted version of the C function
>tabulate", see http://www.statsci.com/Hesterberg/tilting/

Please contact me if you are interested in testing the code.
That web address will no longer work.

The code is part of a package of software for an NSF-funded
project in bootstrap tilting inferences, and includes:

* New functions implementing bootstrap tilting methods for
  diagnostics and confidence intervals.  The big attraction of
  the latter is speed -- they appear to be more accurate with 100
  bootstrap replications than is the BCa interval with 2000 replications.
* Replacements for all the existing bootstrap functions in
  S-PLUS (versions 4.0, 4.1, 4.5, S+2000).  These replacements
  add capabilities and fix bugs.
     This code was not previously available to S+3.4 users; if
  that includes you I believe you'll be pleased with the ease of use
  of this code.
* New functions and updated versions of various S-Plus functions,
  such as mean(), cor(), var(), quantile(), colMeans(), hist(), etc., 
  that allow weights and add other capabilities.

The code is in alpha test form, and is available for S+2000 and S+3.4.
Please contact me if you are interested in testing the code.

While I am happy to have people use the code, I must know who is
testing it so that I can get feedback and let you know if problems
are found.  If you downloaded the code before I moved the web site,
please let me know that you are testing it.

========================================================
| Tim Hesterberg       Research Scientist              |
| timh@statsci.com     MathSoft, Inc.                  |
| (206)283-8802x319    1700 Westlake Ave. N, Suite 500 |
| (206)283-0347 (fax)  Seattle, WA 98109-3044, U.S.A.  |
|                      www.statsci.com/Hesterberg      |
========================================================
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu.  To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message:  unsubscribe s-news

home help back first fref pref prev next nref lref last post