Curve fit

miko1 · ‎11-14-2007

How can I get the errors of the non-linear coefficients from the curve fit express VI?

Jason_Whaylen · ‎11-15-2007

Hi Miko,

Thank you for contacting National Instruments. From what you are describing here, it looks like you are looking for more than the mean squared error that is provided in the express VI. This is the only value that is going to be explicitly provided from this Express VI. To get this value you can drag down the bottom of the VI to increase the number of I/O ports and click to select mean squared error. Sorry if not having error for each non-linear coefficient is a large inconvenience for you.

I hope this helps! Let me know if there is anything else I can help with or clarify. Have a great day!

Jason W.

National Instruments
Applications Engineer

DSPGuy · ‎11-16-2007

Jason is right, your options from the Express VI are limited, but we might be able to work around this. What precisely are you looking for? Do you want the best fit parameters std. deviation? Do you want the confidence intervals for the best fit parameters? What version of LabVIEW are you using?

-Jim

miko1 · ‎11-17-2007

When performing a curve fitting, the parameters of the model should have their errors, and this is what I am looking for.

I am not familiar with the term "confidence intervals" , but I think that the "best fit parameters std. deviation" can be what I am looking for.

I know that the Curve fit Express VI does not supply that but maybe you know how else can I get it?

Thanks for the help.

Miko.

miko1 · ‎11-17-2007

I am using LabView 8.2.

Miko.

chilly_charly · ‎11-17-2007

A discussion related to your question. Hope this helps

Chilly Charly (aka CC)

miko1 · ‎11-23-2007

Thanks it was just what I needed.

Miko.

LabVIEW

Curve fit

Curve fit

Re: Curve fit

Re: Curve fit

Re: Curve fit

Re: Curve fit

Re: Curve fit

Re: Curve fit