Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > comp.graphics.apps.gnuplot > #308
| Path | csiph.com!x330-a1.tempe.blueboxinc.net!usenet.pasdenom.info!news.albasani.net!feeder.erje.net!news-2.dfn.de!news.dfn.de!news.gwdg.de!.POSTED!not-for-mail |
|---|---|
| From | Christoph Bersch <usenet@bersch.net> |
| Newsgroups | comp.graphics.apps.gnuplot |
| Subject | Re: Wrong fit direction / zrange / unreadable graph file |
| Date | Mon, 16 May 2011 11:52:24 +0200 |
| Organization | GWDG, Goettingen |
| Lines | 56 |
| Message-ID | <iqqs4o$fkv$1@gwdu112.gwdg.de> (permalink) |
| References | <01ac512a-8031-41f0-a899-0684927f6c32@n10g2000yqf.googlegroups.com> <iqqpas$cec$1@gwdu112.gwdg.de> <93c9dhFmvmU1@mid.individual.net> |
| NNTP-Posting-Host | mpl1136.mpl.mpg.de |
| Mime-Version | 1.0 |
| Content-Type | text/plain; charset=ISO-8859-1; format=flowed |
| Content-Transfer-Encoding | 7bit |
| X-Trace | gwdu112.gwdg.de 1305539544 16031 141.5.32.136 (16 May 2011 09:52:24 GMT) |
| X-Complaints-To | news@gwdg.de |
| NNTP-Posting-Date | Mon, 16 May 2011 09:52:24 +0000 (UTC) |
| User-Agent | Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.16) Gecko/20110307 Icedove/3.0.11 |
| In-Reply-To | <93c9dhFmvmU1@mid.individual.net> |
| Xref | x330-a1.tempe.blueboxinc.net comp.graphics.apps.gnuplot:308 |
Show key headers only | View raw
On 16.05.2011 11:34, Ingo Thies wrote:
> On 16.05.2011 11:04, Christoph Bersch wrote:
>
>>> n=0
>>> m=-0.3
>>> f(x)=m*x+n
>>
>> Do not set fitting parameters to zero, remove the n=0
>
> Well, that's strange. For a linear fit model I wouldn't expect that an
> initially zero vertical offset should be a problem.
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
This gives me:
------------------------------------------------------------------
Iteration 0
WSSR : 1.08086 delta(WSSR)/WSSR : 0
delta(WSSR) : 0 limit for stopping : 1e-05
lambda : 2.34521
initial set of free parameter values
m = 1.28545
n = 1e-30
********************
After 1 iterations the fit converged.
final sum of squares of residuals : 1.08086
rel. change during last iteration : 0
degrees of freedom (FIT_NDF) : 3
rms of residuals (FIT_STDFIT) = sqrt(WSSR/ndf) : 0.60024
variance of residuals (reduced chisquare) = WSSR/ndf : 0.360288
Singular matrix in Invert_RtR
------------------------------------------------------------------
If you set e.g.
n=1e-5
The fitting works.
Christoph
Back to comp.graphics.apps.gnuplot | Previous | Next — Previous in thread | Next in thread | Find similar
Wrong fit direction / zrange / unreadable graph file Katharina Miwege <k.miwege@googlemail.com> - 2011-05-15 23:59 -0700
Re: Wrong fit direction / zrange / unreadable graph file Christoph Bersch <usenet@bersch.net> - 2011-05-16 11:04 +0200
Re: Wrong fit direction / zrange / unreadable graph file Ingo Thies <ingo.thies@gmx.de> - 2011-05-16 11:34 +0200
Re: Wrong fit direction / zrange / unreadable graph file Christoph Bersch <usenet@bersch.net> - 2011-05-16 11:52 +0200
Re: Wrong fit direction / zrange / unreadable graph file Richard Owlett <rowlett@pcnetinc.com> - 2011-05-16 06:25 -0500
Re: Wrong fit direction / zrange / unreadable graph file Christoph Bersch <usenet@bersch.net> - 2011-05-16 14:44 +0200
Re: Wrong fit direction / zrange / unreadable graph file Ingo Thies <ingo.thies@gmx.de> - 2011-05-16 16:31 +0200
Re: Wrong fit direction / zrange / unreadable graph file Katharina Miwege <k.miwege@googlemail.com> - 2011-05-16 09:01 -0700
Re: Wrong fit direction / zrange / unreadable graph file Christoph Bersch <usenet@bersch.net> - 2011-05-17 08:46 +0200
Re: Wrong fit direction / zrange / unreadable graph file Hans-Bernhard Bröker <HBBroeker@t-online.de> - 2011-05-19 01:34 +0200
Re: Wrong fit direction / zrange / unreadable graph file Hans-Bernhard Bröker <HBBroeker@t-online.de> - 2011-05-19 01:49 +0200
Re: Wrong fit direction / zrange / unreadable graph file Ingo Thies <ingo.thies@gmx.de> - 2011-05-19 11:07 +0200
Re: Wrong fit direction / zrange / unreadable graph file Hans-Bernhard Bröker <HBBroeker@t-online.de> - 2011-05-19 14:02 +0200
Re: Wrong fit direction / zrange / unreadable graph file Hans-Bernhard Bröker <HBBroeker@t-online.de> - 2011-05-19 01:39 +0200
Re: Wrong fit direction / zrange / unreadable graph file Ingo Thies <ingo.thies@gmx.de> - 2011-05-19 10:58 +0200
csiph-web