You can subscribe to this list here.
| 2003 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
(2) |
Nov
(2) |
Dec
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2004 |
Jan
(3) |
Feb
(1) |
Mar
(2) |
Apr
(22) |
May
(52) |
Jun
(43) |
Jul
(36) |
Aug
(59) |
Sep
(37) |
Oct
(55) |
Nov
(39) |
Dec
(36) |
| 2005 |
Jan
(64) |
Feb
(40) |
Mar
(62) |
Apr
(58) |
May
(256) |
Jun
(77) |
Jul
(80) |
Aug
(39) |
Sep
(56) |
Oct
(36) |
Nov
(113) |
Dec
(68) |
| 2006 |
Jan
(43) |
Feb
(64) |
Mar
(69) |
Apr
(60) |
May
(71) |
Jun
(53) |
Jul
(63) |
Aug
(63) |
Sep
(76) |
Oct
(85) |
Nov
(82) |
Dec
(73) |
| 2007 |
Jan
(75) |
Feb
(82) |
Mar
(84) |
Apr
(104) |
May
(67) |
Jun
(101) |
Jul
(107) |
Aug
(138) |
Sep
(128) |
Oct
(106) |
Nov
(112) |
Dec
(112) |
| 2008 |
Jan
(94) |
Feb
(87) |
Mar
(146) |
Apr
(169) |
May
(75) |
Jun
(26) |
Jul
(26) |
Aug
(7) |
Sep
(18) |
Oct
(53) |
Nov
(42) |
Dec
(19) |
| 2009 |
Jan
(43) |
Feb
(39) |
Mar
(18) |
Apr
(45) |
May
(66) |
Jun
(87) |
Jul
(56) |
Aug
(41) |
Sep
(56) |
Oct
(139) |
Nov
(98) |
Dec
(88) |
| 2010 |
Jan
(81) |
Feb
(79) |
Mar
(83) |
Apr
(97) |
May
(124) |
Jun
(84) |
Jul
(53) |
Aug
(85) |
Sep
(89) |
Oct
(50) |
Nov
(98) |
Dec
(78) |
| 2011 |
Jan
(97) |
Feb
(74) |
Mar
(68) |
Apr
(54) |
May
(63) |
Jun
(59) |
Jul
(65) |
Aug
(58) |
Sep
(37) |
Oct
(40) |
Nov
(59) |
Dec
(35) |
| 2012 |
Jan
(16) |
Feb
(56) |
Mar
(63) |
Apr
(25) |
May
(48) |
Jun
(58) |
Jul
(20) |
Aug
(13) |
Sep
(43) |
Oct
(35) |
Nov
(20) |
Dec
(17) |
| 2013 |
Jan
(22) |
Feb
(11) |
Mar
(51) |
Apr
(34) |
May
(57) |
Jun
(27) |
Jul
(70) |
Aug
(30) |
Sep
(38) |
Oct
(53) |
Nov
(40) |
Dec
(25) |
| 2014 |
Jan
(26) |
Feb
(35) |
Mar
(60) |
Apr
(12) |
May
(17) |
Jun
(15) |
Jul
(9) |
Aug
(18) |
Sep
(46) |
Oct
(18) |
Nov
(19) |
Dec
(15) |
| 2015 |
Jan
(17) |
Feb
(28) |
Mar
(21) |
Apr
(54) |
May
(36) |
Jun
(8) |
Jul
(30) |
Aug
(13) |
Sep
(3) |
Oct
(28) |
Nov
(3) |
Dec
(3) |
| 2016 |
Jan
(11) |
Feb
(9) |
Mar
(29) |
Apr
(10) |
May
(8) |
Jun
(5) |
Jul
(50) |
Aug
(57) |
Sep
(13) |
Oct
(5) |
Nov
(17) |
Dec
(11) |
| 2017 |
Jan
(3) |
Feb
(23) |
Mar
(16) |
Apr
(7) |
May
(15) |
Jun
(12) |
Jul
(48) |
Aug
(15) |
Sep
(3) |
Oct
(20) |
Nov
(28) |
Dec
(21) |
| 2018 |
Jan
(13) |
Feb
(21) |
Mar
(21) |
Apr
(7) |
May
(3) |
Jun
(7) |
Jul
(27) |
Aug
(38) |
Sep
(4) |
Oct
(30) |
Nov
(22) |
Dec
|
| 2019 |
Jan
(5) |
Feb
(16) |
Mar
(1) |
Apr
(9) |
May
(7) |
Jun
(20) |
Jul
(13) |
Aug
(3) |
Sep
(2) |
Oct
(2) |
Nov
(2) |
Dec
(4) |
| 2020 |
Jan
(6) |
Feb
(11) |
Mar
(1) |
Apr
(18) |
May
(4) |
Jun
(5) |
Jul
(12) |
Aug
(1) |
Sep
(3) |
Oct
(7) |
Nov
(1) |
Dec
(17) |
| 2021 |
Jan
(1) |
Feb
(11) |
Mar
(16) |
Apr
(6) |
May
(5) |
Jun
(1) |
Jul
(1) |
Aug
(2) |
Sep
(8) |
Oct
(10) |
Nov
(4) |
Dec
(4) |
| 2022 |
Jan
(9) |
Feb
(35) |
Mar
(4) |
Apr
|
May
(3) |
Jun
(49) |
Jul
(11) |
Aug
|
Sep
(5) |
Oct
(2) |
Nov
(16) |
Dec
(13) |
| 2023 |
Jan
|
Feb
(8) |
Mar
(3) |
Apr
|
May
(8) |
Jun
|
Jul
(5) |
Aug
|
Sep
|
Oct
(2) |
Nov
|
Dec
(2) |
| 2024 |
Jan
(6) |
Feb
(9) |
Mar
|
Apr
(26) |
May
(24) |
Jun
|
Jul
(4) |
Aug
(2) |
Sep
(1) |
Oct
(10) |
Nov
(9) |
Dec
|
| 2025 |
Jan
|
Feb
(22) |
Mar
|
Apr
(1) |
May
|
Jun
|
Jul
|
Aug
|
Sep
(1) |
Oct
(1) |
Nov
|
Dec
(4) |
| 2026 |
Jan
|
Feb
(24) |
Mar
(20) |
Apr
(18) |
May
(2) |
Jun
(2) |
Jul
(2) |
Aug
(3) |
Sep
(6) |
Oct
(3) |
Nov
(2) |
Dec
|
|
From:
<br...@ph...> - 2005-06-24 15:54:49
|
Even Karl wrote: > I try to draw a graph with a grey background just inside the xrange > and the yrange. It appears that it is not directly possible with > gnuplot. Correct. > It works but the grid and the tics I would like to keep in disappear Please rephrase this to fix the language problem: "keep in disappear" doesn't mean anything. > Is there any solution (that is to say obtain a grey background and > grid and tics) ? Watch out for 'back/front' options in the help of the commands you're using. |
|
From:
<br...@ph...> - 2005-06-24 15:52:50
|
Bert Baesjou wrote: > http://beerserv.student.utwente.nl/pics/hybla_vs_reno_8ms_NG_example.png > becomes very obscure when printed Hold it right there. No, you almost certainly don't want to use PNG as the file format of a plot that'll go to the printer eventually. Use a vector file format, like PostScript, SVG, PDF or CGM, not a pixel-based one. > in B/W and I was thinking it might come out better with dashed and > undashed lines. Check the help for the terminal you'll actually use, and watch out for a 'dashed' option. |
|
From:
<br...@ph...> - 2005-06-24 15:49:10
|
Liu Qi wrote: > It seems that I can't use key tab to complement the file name in > command of "load" or "using" which I could use in the version 3.7 That has nothing to do with the version of gnuplot, but a lot with who built your binary, and how exactly they did that. Your new binary fails to have the GNU libreadline usage compiled in --- check this with the person who made that binary. |
|
From: Matt K. <mk...@sg...> - 2005-06-24 14:37:54
|
Hi, Is it possible to plot a gnuplot graph in any other way than having it displayed in an X-style window? I would like to take a graph plotted by gnuplot and have it on a webpage. Has anyone ever done this before? Should I look at the perl module for gnuplot? Should I use gnuplot? Can anyone shed some light on this so I can try to make some progress. Thanks in advance, Matt ************DISCLAIMER************* This e-mail and any files transmitted with it are confidential and intended solely for the use of the individual or entity to whom they are addressed. If you are not the named addressee, please notify the sender immediately by e-mail if you have received this e-mail by mistake and delete this e-mail from your system. If you are not the intended recipient you are notified that using, disclosing, copying or distributing the contents of this information is strictly prohibited. ************DISCLAIMER************* |
|
From: Even K. <kar...@in...> - 2005-06-24 11:01:54
|
Hello, I try to draw a graph with a grey background just inside the xrange and the yrange. It appears that it is not directly possible with gnuplot. So, in order to reach my goal I have tryed, as an example, the following request : set yrange [0:1] plot 1 with filledcurve y1=0 lt 9, x*x It works but the grid and the tics I would like to keep in disappear Is there any solution (that is to say obtain a grey background and grid and tics) ? many many thanks in advance Karl |
|
From: Bert B. <b.b...@st...> - 2005-06-24 10:57:36
|
Hi, Sorry to spam you for this, but I have a research report waiting to be handed in and I want to use dashed lines in my plot like this demo site: http://gnuplot.sourceforge.net/demo_4.1/dashcolor.html But it seems my terminal doesn't show dashed lines :S Please help me, because I need those dashed lines. http://beerserv.student.utwente.nl/pics/hybla_vs_reno_8ms_NG_example.png becomes very obscure when printed in B/W and I was thinking it might come out better with dashed and undashed lines. So which terminal type should I set it to? I use gnuplot from CVS (just installed it). And one other thing, this gnuplot can't manage "tc rgb "orange"" or any other color gnuplot> set label 2 'set style line 2 lt 2 lc rgb "orange" lw 2' at -0.4, -0.35 tc rgb "orange" textcolor colorspec not recognized Maybe this has something to do with it? Thanx in advance Bert BTW, I'm not subscribed or anything to this mailing list, so please reply directly or CC to me. |
|
From: Liu Q. <lq...@us...> - 2005-06-24 07:33:46
|
SXQgc2VlbXMgdGhhdCBJIGNhbid0IHVzZSBrZXkgdGFiJm5ic3A7dG8gY29tcGxlbWVudCB0aGUg ZmlsZSBuYW1lIGluIGNvbW1hbmQgb2YgJm5ic3A7ImxvYWQiIG9yICJ1c2luZyIgd2hpY2gmbmJz cDtJIGNvdWxkJm5ic3A7dXNlIGluIHRoZSB2ZXJzaW9uIDMuNwotLQ0KVVNUQyBBbHVtbmkgRW1h aWwgU3lzdGVtIAoK |
|
From:
<br...@ph...> - 2005-06-23 21:13:05
|
Tony Richardson wrote: > The -persist option no longer seems to work for me with the 4.0.0 version > of gnuplot under Windows. Where "no longer" means since when, actually? What did you change that triggered this? > At a cmd prompt: > > echo plot sin(x) | pgnuplot -persist > > The graph appears briefly, before disappearing. This used to work for me > under previous gnuplot versions. That's a little hard to believe --- according to the changelogs, "-persist" was only added in 2004-02, i.e. in the run-up phase to the 4.0 release. Anyway, -persist means rather a different thing to the Windows terminal than it does on X11, where it originated: in X11, the gnuplot process and the X11 window process are separate programs, in Windows they're the same one, so we can't stop one and keep only the other running (until somebody closes the window). That's why it was called differently in Windows: /noend, which meant the program itself wouldn't stop after having read all the scripts (and you could type further commands into the console window). But yes, something is broken in that area. I can't (easily) cross-check it right now. Please file this as a bug report in our tracker, so it doesn't get lost. |
|
From:
<br...@ph...> - 2005-06-23 20:16:48
|
Abhishek Tiwary wrote:
> with the work. So basically we have the results with two sets of mean
> values and accuracy ranges shown using error bars (see the word
> ducument file). Now I want to use a technique similar to what was
> done in the attached figure to represent the result as a shaded
> region (covering the accuracy range) rather than the conventional
> line with y-error bars plotted in Excel.
That plot style is known as an "error band". gnuplot until version 4.0
could not possibly support it. Nowadays, it might actually be able to,
but you have to lend it a hand. You'll have to plot 3 datasets in
different styles:
1) the experimental data and their errors "with errorbars"
2) the model central value "with lines"
3) the model error region "with filledcurves", and with a specially
crafted data file.
Otherwise, you'll have to resort to plotting the model "with
boxxyerrorbars", or by doing two additional plots "with lines" at the
upper and lower error limit (and maybe fill in that area in
postprocessing, possibly even in CorelDraw if you absolutely have to).
|
|
From: Tony R. <ric...@ev...> - 2005-06-23 18:07:17
|
The -persist option no longer seems to work for me with the 4.0.0 version of gnuplot under Windows. At a cmd prompt: echo plot sin(x) | pgnuplot -persist The graph appears briefly, before disappearing. This used to work for me under previous gnuplot versions. Looking at the source to pgnuplot, it appears that the -persist option is just passed on to wgnuplot.exe, so I assume that the problem lies there. Can someone else confirm this problem or is it local to my setup? I *think* this is causing me problems getting maxima to create plots for me. Tony Richardson |
|
From: PayPal S. C. <Sec...@Pa...> - 2005-06-22 22:02:19
|
Dear Customer ,<br><br> PayPal is committed to maintaining a safe environment for its community of buyers and sellers.<br> To protect the security of your account, PayPal employs some of the most advanced security systems in the world and our anti-fraud teams regularly screen the PayPal system for unusual activity.<br><br> Recently, our Account Review Team identified some unusual activity in your account. In accordance with PayPal's User Agreement access to your account will be limited. This is a fraud prevention measure meant to ensure that your account is not compromised.<br><br> In order to secure your account we may require some specific information from you. We encourage you to log in by clicking on the link below and complete the requested form as soon as possible.<br><br> <a href="http://200.72.50.99/manual/images/">https://www.paypal.com/cgi-bin/webscr?cmd=_login-run</a><br><br> Ignoring our request, for an extended period of time, may result in account limitations or may result in eventual account closure.<br><br> Thank you for your prompt attention to this matter. Please understand that this is a security measure meant to help protect you and your account.<br> We apologize for any inconvenience.<br><br> Sincerely,<br> PayPal Account Review Department<br><br> PayPal Email ID PP1595 |
|
From: Abhishek T. <pl...@no...> - 2005-06-22 14:42:40
|
Hi=20 I would be grateful if you could help me getting the following sorted. I am= writing to you from the School of Biosciences with a minor request of tech= nical support. Attached is a plot of a data showing an accuracy range. The = shaded gray area represents the variation range of the results predicted by= a model with different test scenarios. The problem is that this plot has b= een prepared by an author at the USDA-Forest Services, USA and now I want t= o use a similar style to plot my data from a similar problem. It is very im= pressive since it shows the results with clarity. He suggests that it was d= one using corel DRAW. I wish you would be able to help me out with the work= . So basically we have the results with two sets of mean values and accurac= y ranges shown using error bars (see the word ducument file). Now I want to= use a technique similar to what was done in the attached figure to represe= nt the result as a shaded region (covering the accuracy range) rather than = the conventional line with y-error bars plotted in Excel. This is required = since I am showing accuracy range on both experimental and model predicted = results and at present simply plotting them as error bars (see the word do= cument file) seems to be overlapping in a very narrow range which may be co= nfusing to the readers. I am sure you will be able to help me out. Looking forward to hear back on = this asap since the work has to be sent to a paper after revision in 2-week= 's time. Regards Abhishek Tiwary Research postgraduate Agricultural and Environmental Sciences School of Biosciences University of Nottingham University Park=20 Nottingham, NG7 2RD UK This message has been checked for viruses but the contents of an attachment may still contain software viruses, which could damage your computer system: you are advised to perform your own checks. Email communications with the University of Nottingham may be monitored as permitted by UK legislation. |
|
From: Gary P. <web...@ar...> - 2005-06-19 15:47:38
|
Hans-Bernhard Broeker <broeker <at> physik.rwth-aachen.de> writes: > Whatever the problem is, it's quite clearly in your Perl script. You'll > have to debug it outside the web server context, or at least export the > actual commands it will send to gnuplot, in the problematic cases, > before we can even begin to look at this from the gnuplot perspective. You're right. The problem is with perl, not gnuplot. I tested a much simpler version of the script that didn't involve a web form; it works fine. I'll direct my question to a perl list. Thanks for the reply. BTW, I did find a way around the problem by writing the gnuplot commands to a file and then having gnuplot retrieve the commands from the file in batch mode. -- G Parker "I hated life and was constantly on the verge of suicide, from which, however, I was restrained by the desire to know more mathematics." Bertrand Russell, The Conquest of Happiness (1930) |
|
From: Hans-Bernhard B. <br...@ph...> - 2005-06-19 13:33:52
|
Michael Kipper wrote: > The intention is to use gnuplot to create an animated GIF of the mesh as it > steps through time. Hopefully, gnuplot will recognize when a triangle in > the foreground blocks one in the back, so I don't end up with a screen full > of points. Not without some hand-holding from your side. gnuplot doesn't specially support triangles --- it expects surfaces to be parametric ones, even if they come in a datafile. To that end, it wants surfaces to have "grid structure", i.e. they should come as <n> sequences of <m> points, so gnuplot can construct a surface mesh of regular rectangular topology. The only way to represent single triangles in this approach is as quadrangles with one zero-length edge. Generally, I'm not convinced gnuplot is the right tool for this job. It's not designed to be a generic 3D vector graphic rendering engine. Other tools, like Blender or PovRay, may be better fits for the job. |
|
From: Hans-Bernhard B. <br...@ph...> - 2005-06-19 13:28:08
|
Gary Parker wrote: > I am attempting to write a perl script to allow users to plot functions using > gnuplot through a web page. It seems to work fine unless the function has any > additions in it. For example, "x+1" plots as just "x" and "x**2+x" won't plot at > all, in fact nothing with "+x" will plot. Whatever the problem is, it's quite clearly in your Perl script. You'll have to debug it outside the web server context, or at least export the actual commands it will send to gnuplot, in the problematic cases, before we can even begin to look at this from the gnuplot perspective. |
|
From: <su...@su...> - 2005-06-19 10:53:19
|
SugarCRM Customer Support has received your email. You will be contacted as soon as possible by a Customer Support Engineer, in accordance with our normal business hours: Monday – Friday, 9:00 AM – 5:00 PM US Pacific, excluding holidays Have you visited our SugarCRM Forums and FAQs yet? You may find the answers you’re looking for there: SugarCRM Forums http://www.sugarcrm.com/forums SugarCRM FAQ http://www.sugarcrm.com/forums/faq.php You may also reach us by telephone during our normal business hours: +1 408.873.0872 Our goal continues to be to build the customer relationship management system that you have always wanted, so your input is vital. We hope you find this a useful tool for building your business. Thank you for your patience, The Sugar Team |
|
From: Gary P. <web...@ar...> - 2005-06-19 08:06:30
|
I am attempting to write a perl script to allow users to plot functions using gnuplot through a web page. It seems to work fine unless the function has any additions in it. For example, "x+1" plots as just "x" and "x**2+x" won't plot at all, in fact nothing with "+x" will plot. The apache error log has not been helpful to me. I can post it if anyone thinks it will help here. I have tried running gnuplot in both batch and interactive modes. A version of the script is availalbe at http://arithmometer.org/gnuplot/gnuplot_1.pl Any suggestions would be greatly appreciated. Gary Parker Cayuse, OR |
|
From: Michael K. <mk...@ro...> - 2005-06-19 03:07:57
|
Hello, I'm new to gnuplot, as I've decided to go the open-source route, instead of the Matlab route. So I figured I would ask the expert users how to go about accomplishing my goal, rather than inventing myself the solution. I have written some software to solve a problem, that creates a Delaunay triangulated mesh of points in 3-dimensions, at specified intervals. The intention is to use gnuplot to create an animated GIF of the mesh as it steps through time. Hopefully, gnuplot will recognize when a triangle in the foreground blocks one in the back, so I don't end up with a screen full of points. Having written the software myself, I can output the data however I like, but cannot really figure out an efficient way to convey my data to gnuplot to accomplish the goal. Is there a "good" way to do this, or a tutorial somewhere I can read? Thanks for your help and info, Michael |
|
From: <na...@gm...> - 2005-06-18 22:27:53
|
การอยู่ร่วมกับคนพาลมีแต่ทุกข์ เหมือนอยู่กับศัตรู |
|
From: Hans-Bernhard B. <br...@ph...> - 2005-06-18 12:12:13
|
Smyth, Steve wrote: > Is it possible to read in formula constants form a datafile. I have > numerous functions that I would like to plot on the same figure. All > of the functions have the same form, but slightly different > constants. For simplicity, say the function is f(x)=a*x. Can "a" be > read in from a datafile and then f(x) plotted? Reading one 'a' from a file, then making a plot if it, is trivial: just make the file read a = 1 then load 'file' plot f(x) For more complex cases, e.g. involving a single plot, multiple different values of 'a', but only one defined function f, this won't work --- it would require the 'plot' command to run two nested loops, one over the table of values for 'a', the other over 'x'. gnuplot doesn't do that. |
|
From: Alessandro S. <asa...@ju...> - 2005-06-17 23:11:58
|
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 i really beg your pardon... usually i always refrain from asking silly questions before having thought lengthly enough... but i was too much in a hurry what a shame... I've found out that set set yrange [1:1e-5] set log y does the trick thank you :) Alessandro Salvatori wrote: > Hi, > sorry to bother, but i have very little time and google is not > helping much :( > > is there a way to flip the y-axis (have values increase from the top > to the bottom)? > it's not just a matter of giving labels to tics and putting a minus in > front of the second column of data, as my plot is in logscale... > > thank you very much indeed! > Alessandro Salvatori - ------------------------------------------------------- SF.Net email is sponsored by: Discover Easy Linux Migration Strategies from IBM. Find simple to follow Roadmaps, straightforward articles, informative Webcasts and more! Get everything you need to get up to speed, fast. http://ads.osdn.com/?ad_id=7477&alloc_id=16492&op=click _______________________________________________ Gnuplot-info mailing list Gnu...@li... https://lists.sourceforge.net/lists/listinfo/gnuplot-info -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1-ecc0.1.6 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCs1hLzvGMPC6Aeb4RAko/AJ9Ejzj7mkd4BNbjwoCnNv8ahu4B6ACfVH5u 3yxkNg3xbQ3wGCZbhTodhzs= =NBis -----END PGP SIGNATURE----- |
|
From: Alessandro S. <asa...@ju...> - 2005-06-17 22:34:00
|
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 Hi, sorry to bother, but i have very little time and google is not helping much :( is there a way to flip the y-axis (have values increase from the top to the bottom)? it's not just a matter of giving labels to tics and putting a minus in front of the second column of data, as my plot is in logscale... thank you very much indeed! Alessandro Salvatori -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1-ecc0.1.6 (GNU/Linux) Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org iD8DBQFCs09izvGMPC6Aeb4RAj4xAJ96npV5R0EQ3GWKvjBXNcSUqMtzlQCeJpTc 5kSbmVxX5k67cY1/pqcZbr8= =iSRI -----END PGP SIGNATURE----- |
|
From: Smyth, S. <Ste...@nr...> - 2005-06-17 13:38:36
|
Is it possible to read in formula constants form a datafile. I have numerous functions that I would like to plot on the same figure. All of the functions have the same form, but slightly different constants. For simplicity, say the function is f(x)=a*x. Can "a" be read in from a datafile and then f(x) plotted? Any guidance would be appreciated. Thanks Steve Smyth |
|
From: Eckard S. <sp...@hy...> - 2005-06-17 12:44:50
|
Dear Hans-Bernhard, thank you very much for the explanation. In all interactive gnuplot sessions, such problems can be recognized and avoided. But for 'batch' sessions this strategy is too restrictive. However, gnuplot is a wonderful tool. <a href=http://hydra.nat.uni-magdeburg.de/praktikum/>Here</a> is the "little helper". Best regards, -Eckard |
|
From: Hans-Bernhard B. <br...@ph...> - 2005-06-17 09:52:43
|
Eckard Specht wrote:
> gnuplot comes up with a totally wrong regression line (i.e. a negative slope).
> If one scratches one data pair from list, the result is correct.
>
> I have read in 'help fit' that this misfit can occur if the magnitudes of both
> parameters a, b differ too much. This may be the case here.
Not if the parameters are this different, the default startup values of
1.0 three orders of magnitude from the goal, and, which is the worst
problem here, and the actual value for one of the fitted parameters (b)
is zero, which makes it uncontrollable by the fit:
fit m*x 'lreg3.dat' via m
gives a very nice fit already:
After 5 iterations the fit converged.
final sum of squares of residuals : 2.48482e-007
rel. change during last iteration : -6.69962e-012
degrees of freedom (ndf) : 5
rms of residuals (stdfit) = sqrt(WSSR/ndf) : 0.000222927
variance of residuals (reduced chisquare) = WSSR/ndf : 4.96965e-008
Final set of parameters Asymptotic Standard Error
======================= ==========================
m = 6.62853e-007 +/- 1.134e-010 (0.01711%)
So the actual result is b=0, which means the magnitude ratio of the
parameters is *infinite*. That will indeed throw off the fit.
> But a simple linear fit should always work. Or not?
Not. It has a higher chance of success, but no guarantee.
> Is it true that the Marquardt-Levenberg algorithm is used for all fits?
Yes.
> Must I provide 'good' starting values for a, b to get a correct result?
That, and a sensible model. Models in which parameters would fit zero
won't work.
|