There is a function in excel called 'linest' that will perform a multiple linear regression with a single y column of data and multiple x columns. Is there an equivilant in Lavview?

[sjh]

That's working very well - we are getting very close correlation with the data. (we run it back through to see the match).

Thanks again.

[sjh]

As a post script, now the system is working we will start running a comparative set of code just using the 3 base elements of the equation.

I will report back!

[huz]

All, I am having a similar problem. I am using the Regression Tool in Data Analysis Toolpak in Excel. The results from that program does not match the the Labview results.  In LabView, I am using the General LS Linear Fit function. From this tread discussion, it seems to me that we have to to normalize the Y vector and divide the H matrix by the same value and then put the resultant matrix through the General LS linear Fit function. Am I understanding this correctly? Also, in my problem, no matter what method I use, i get the same results (in terms of coefficients). Is this common?

Any help would be greatly appreciated! 

Regards

Huz 

[sjh]

Hi.

Sorry but I am not 100% clar on your problem, but I hope this helps.

I moved completely away for the GS linear fit and moved across to a vi call 'Solve linear equations.vi. I can post if that helps.  

This gets results that are comparable - but not exactly the same as Excel.

Hope that helps.

[huz]

Hello,

Do you mind posting it. I have been working on this problem for two weeks now and I have not had much luck getting a good resolution.

Regards

HUz

[sjh]

That is the vi I am now using

Message Edited by sjh on 11-09-2009 03:04 PM