SMath Studio Forum
»
SMath Studio
»
Samples
»
Linear Regression forced through origin
Rank: Member Groups: Registered
Joined: 28/03/2023(UTC) Posts: 26 Location: San Miguel de Tucumán Was thanked: 3 time(s) in 3 post(s)
|
Hi, I am running Smath Studio on Arch Linux and I decided to upload some work, in order to share with you all. I will very appreciate some feedback,because some values are not the same in the examples I choosen. Kind regards, linfitforced1.sm (85kb) downloaded 17 time(s). linfitforced.sm (259kb) downloaded 17 time(s).
|
|
|
|
Rank: Guest
Groups: Registered
Joined: 04/07/2015(UTC) Posts: 6,866 Was thanked: 981 time(s) in 809 post(s)
|
Originally Posted by: Javier Ochoa I will very appreciate some feedback Hello Xavier Not sure what you are doing/attempting. As it looks, you have created a non linear data set. You can refit brute force simple, attached. Remember: you fit experimental data. Cheers ... Jean. linfitforced (1) Fit .sm (14kb) downloaded 11 time(s).
|
1 user thanked Jean Giraud for this useful post.
|
|
|
Rank: Advanced Member Groups: Registered
Joined: 28/08/2014(UTC) Posts: 1,356 Was thanked: 815 time(s) in 516 post(s)
|
Hola Javier. The values for a and b are all the same. It seems that for one worksheet you use the standard deviation for one sample and the other for the population, both of which are different (see Bessel's correction, for example). Also notice that the plotG function is for old versions of SMath, in the new ones you can graph the X and Y vectors with augment( X,Y,"o" ) or augment( X,Y,"o",10,"red" ). Best regards. Alvaro.
|
1 user thanked Razonar for this useful post.
|
|
|
Rank: Member Groups: Registered
Joined: 28/03/2023(UTC) Posts: 26 Location: San Miguel de Tucumán Was thanked: 3 time(s) in 3 post(s)
|
Hi Jean and Alvaro, Thank you for the feedback, I tried to use solvers with problems which I have the answer. In the first worksheet I follow the method proposed by the authors, which involves the use of the equation provided by them, and the values of a and b are the same on both worksheets. The other worksheet follow the guidance provided in the forum through a couple of files uploaded to the forum called linfit.sm and linfit.pdf.
The purpose of solving the same equations with two different methods in two different worksheet allowed me to learn Smath, than any other main reason.
I could not install the Statistical plugin in Arch Linux so I decided to play with several ways to find the answer and give some statistic information.
Regards
|
|
|
|
SMath Studio Forum
»
SMath Studio
»
Samples
»
Linear Regression forced through origin
Forum Jump
You cannot post new topics in this forum.
You cannot reply to topics in this forum.
You cannot delete your posts in this forum.
You cannot edit your posts in this forum.
You cannot create polls in this forum.
You cannot vote in polls in this forum.