Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
To increase the number of significant digits in the curve fitting tool box

Subject: To increase the number of significant digits in the curve fitting tool box

From: Janani Chander

Date: 21 Jan, 2013 07:16:08

Message: 1 of 3

Hi,

I would like to if there is anyway to increase the number of significant digits in curve fitting. I tried to fit and got a fittiong co-efficient as below.
inear model Poly1:
     f(x) = p1*x + p2
       where x is normalized by mean 0.0002051 and std 0.0002143
Coefficients (with 95% confidence bounds):
       p1 = 8.119e-05 (8.043e-05, 8.195e-05)
       p2 = -43.82 (-43.82, -43.82)

But for the confidence bound is the same as co efficient, is there anyway i can increase the significant digits in the parameters?

Subject: To increase the number of significant digits in the curve fitting tool box

From: Torsten

Date: 21 Jan, 2013 10:15:09

Message: 2 of 3

"Janani Chander" wrote in message <kdipvo$nef$1@newscl01ah.mathworks.com>...
> Hi,
>
> I would like to if there is anyway to increase the number of significant digits in curve fitting. I tried to fit and got a fittiong co-efficient as below.
> inear model Poly1:
> f(x) = p1*x + p2
> where x is normalized by mean 0.0002051 and std 0.0002143
> Coefficients (with 95% confidence bounds):
> p1 = 8.119e-05 (8.043e-05, 8.195e-05)
> p2 = -43.82 (-43.82, -43.82)
>
> But for the confidence bound is the same as co efficient, is there anyway i can increase the significant digits in the parameters?

Take a look at
http://compgroups.net/comp.soft-sys.matlab/the-number-of-significant-figures-in-cur/808004

Best wishes
Torsten.

Subject: To increase the number of significant digits in the curve fitting tool box

From: Steven_Lord

Date: 22 Jan, 2013 05:06:14

Message: 3 of 3



"Janani Chander" <chinuchander84@rediffmail.com> wrote in message
news:kdipvo$nef$1@newscl01ah.mathworks.com...
> Hi,
>
> I would like to if there is anyway to increase the number of significant
> digits in curve fitting. I tried to fit and got a fittiong co-efficient
> as below.
> inear model Poly1:
> f(x) = p1*x + p2
> where x is normalized by mean 0.0002051 and std 0.0002143
> Coefficients (with 95% confidence bounds):
> p1 = 8.119e-05 (8.043e-05, 8.195e-05)
> p2 = -43.82 (-43.82, -43.82)
>
> But for the confidence bound is the same as co efficient, is there anyway
> i can increase the significant digits in the parameters?

Note that this is simply _displaying_ the coefficient using a small number
of decimal places. The actual coefficients are stored in the fit object in
double precision; save/export the fit object to the workspace and use the
COEFFVALUES function to retrieve them. The CONFINT function will give you
the confidence bounds. You may also need to change the display FORMAT.

--
Steve Lord
slord@mathworks.com
To contact Technical Support use the Contact Us link on
http://www.mathworks.com

Tags for this Thread

No tags are associated with this thread.

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us