Path: csiph.com!x330-a1.tempe.blueboxinc.net!usenet.pasdenom.info!gegeweb.org!newsfeed.kamp.net!newsfeed.kamp.net!fu-berlin.de!uni-berlin.de!individual.net!not-for-mail
From: Ingo Thies <ingo.thies@gmx.de>
Newsgroups: comp.graphics.apps.gnuplot
Subject: Re: Wrong fit direction / zrange / unreadable graph file
Date: Mon, 16 May 2011 16:31:18 +0200
Lines: 32
Message-ID: <93cqpmF1a3U1@mid.individual.net>
References: <01ac512a-8031-41f0-a899-0684927f6c32@n10g2000yqf.googlegroups.com> <iqqpas$cec$1@gwdu112.gwdg.de> <93c9dhFmvmU1@mid.individual.net> <iqqs4o$fkv$1@gwdu112.gwdg.de>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
X-Trace: individual.net 0RFa4jYBVJS2XJjCn0ZizQaaKcmgzykyukK9vpUKCvfPsUuzIR
Cancel-Lock: sha1:piPkoR9IZcrSrdXsC24hckzqJzw=
User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.2.17) Gecko/20110424 Thunderbird/3.1.10
In-Reply-To: <iqqs4o$fkv$1@gwdu112.gwdg.de>
Xref: x330-a1.tempe.blueboxinc.net comp.graphics.apps.gnuplot:312

On 16.05.2011 11:52, Christoph Bersch wrote:

> To reproduce the problem:
> 
> data.dat:
> 1 2.1
> 2 2.9
> 3 4.2
> 4 5.05
> 5 6
> 
> n = 0
> f(x) = m*x + n
> fit f(x) 'data.dat' via m,n

Strange. I see no reason for this since n is merely an additional offset
which could, depending on the function, even be negative. And the DNLS1E
routine from SLATEC doesn't have any problems here. How is fitting done
in gnuplot in particular?

BTW DNSL1E returns the following best-fit results, even with initial
n=m=0.0:

m = 0.995 +/- 0.041
n = 1.065 +/- 0.135

as does gnuplot with non-zero initial n. Maybe that routine has some
singular matrix trap which gnuplot doesn't have.


Ingo