Does anyone know if this maple function works in SMATH? I cannot get it to work.
File non trovato.

If not available, is there another similar regression fit function available?

Sorry about that. Update to sm file.
File non trovato.File non trovato.

I am really struggling. It shouldn't be this hard.
This version of Maple 6 regression fit also does not work.
Maybe someone could give me examples of the five input arguments to the SMATH Fit(5) function as noted in the figure.

File non trovato.

As always, any help is appreciated. I really want to get away from Mathcad 15 because there is no longer any support.

It is possible to use this function, but it is difficult. To do this, you need to include the stats package in the with.inс file. By default, not all packages are included in the plugin and you must manually specify the required ones in the plugin folder (bin\with.inc):




Unfortunately, the Maple syntax is difficult to replicate in a document, so the ability to use the symbol engine is limited. I'll see if I can somehow use this solution with vectors from the document. Now I recommend using alternative solutions, which I hope will be offered soon.

Yikes, that is beyond me.

What about the built-in Fit(5) function question?

This is what I am trying to achieve, but it defeats my purpose of getting away from Mathcad 15.

File non trovato.

Surly, there is a simple way to fit data with various functions in SMATH, but maybe not.

Hi. In the attached how to use Fit(5), which requires Maxima plugin, and al_nleqsolve applied to an overdetermined system.

CLIMATE CHANGE.sm (19,28 KiB) scaricato 1593 volta(e).

About maple, as far I know, in the version 6 the equation to fit must be linear in the unknown parameters, as it don't have the uppercase 'Fit' package, but the old 'fit' one.

Best regards.
Alvaro.

Thanks for the info; however, I added both plugins and the maxima calculation failed for some reason.
File non trovato.

My copy shows both of the plugins are available.

The Maxima plugin is just the interface (works only under Windows) to standard Maxima. Maxima must be installed separately and SMath must be told the path to Maxima. Follow the link in my signature, there you find instructions.

Wrote

If not available,
is there another similar regression fit function available ?

Under the hood, your model is very reflexive. Thus not easy to fit.
... not easy to fit means various coefficients fit as well.
Differently, Cholesky polynomial fits as well, not reflexive.
Matter of preference.
Climate change is BS. Earth entropy is increasing till much colder.
Global warming [HadCRU] proves the decrease °C since ~ 2010.
Cheers ... Jean.

Page2 Climate.sm (59,43 KiB) scaricato 1448 volta(e).
Inst_HadCRUt4.sm (267,2 KiB) scaricato 1341 volta(e).

I agree. See my attached report.
CLIMATE MODELS.pdf (1,5 MiB) scaricato 1054 volta(e).

I don't have MAXIMA. Are you telling me that both of these built in SMATH functions require Maxima?

File non trovato.

File non trovato.

Since I don't have MAXIMA, why do they show up as available?

So, I have come to the conclusion that there are no built-in curve fitting routines in SMATH that will allow me to do an exponential fit like I do in Mathcad 15.

I assume that means I must write my own since nothing offered so far gives a good fit like the Mathcad exponential fit.

Thanks for all your responses.

Wrote

So, I have come to the conclusion that there are no built-in curve fitting routines in SMATH

That's right, Smath has no fitting plugin. However, we miss nothing.
miss nothing: Explain ...
Smath fitting techniques is a HUGE collection of advanced utilities.
By far more capable than MCD 11 unless they have implemented many more than Given/Minerr.
Please confirm you can download from the forum after disabling firewall(s).
Visit Samples ... LMSA Genfit attached few days ago.
Cheers ... Jean.

... by fitting, I mean fitting raw data sets.

Hello

I think you can use the Least Squares algorithm to fit the data.



CLIMATE CHANGE WORKING_CBG.sm (35,53 KiB) scaricato 1417 volta(e).


Best Regards

Carlos

... Smath Thurber fit

Extrapolation of your 2020 data set is anon-sense.
Nothing yet, indicates it will be logistic asymptotic,
may be returning a Gaussian or crippled Gaussian.
The last part of the data set is noisy but has a trend.

Wrote

It is possible to use this function, but it is difficult. To do this, you need to include the stats package in the with.inс file. By default, not all packages are included in the plugin and you must manually specify the required ones in the plugin folder (bin\with.inc):

with(linalg):with(inttrans):with(plots):with(stats):

Unfortunately, the Maple syntax is difficult to replicate in a document, so the ability to use the symbol engine is limited. I'll see if I can somehow use this solution with vectors from the document. Now I recommend using alternative solutions, which I hope will be offered soon.

Dear Uni I tried to duplicate your example after adding with(stats) to the plugin\bin\with.inc Unfortunately I seem to do something wrong. Could you assist me? Thanks in advance. I have added my attemptMapleFitTest.sm (3,75 KiB) scaricato 1332 volta(e).

For your little 4 points data set
1. fit linterp(vx,vy,x) but you don't have an export
2. fit Cholesky and export the fitted function.
Jean.

Wrote

So, I have come to the conclusion that there are no built-in curve fitting routines in SMATH that will allow me to do an exponential fit like I do in Mathcad 15. ....

Hi Reg. The solution proposed at the post #4 in the file { CLIMATE CHANGE.sm (19,28 KiB) scaricato 1593 volta(e). } only uses an standard SMath plugin, for al_nleqsolve .

Wrote

I assume that means I must write my own since nothing offered so far gives a good fit like the Mathcad exponential fit. ...

In this graph, the solutions of SMath, Maxima and Mathcad are compared. SMath's solution seems as valid to me as Mathcad's.



Best regards.
Alvaro.

Wrote

I assume that means I must write my own since nothing offered so far gives a good fit like the Mathcad exponential fit

Mahcad exponential fit is essentially based on LM resident code.
You can do same in Smath from Genfit techniques or Carlos LM.
All MCD fits done in the Mathsoft Collaboratory have been done in Smath.
Smath Genfit compendium is lot more immense.
Jean.

Jean,
You have my file. If what you say is true, please post an example of an exponential fit to my data.

Thanks