LabVIEW

cancel
Showing results for 
Search instead for 
Did you mean: 

how to use regression

i have a two data which forms a cluster of two elements, which in turn is then connected to a graph. However, the line plotted in this graph is not the best fit line. Hence, i decided to include regression. However, there is always the problem that my original data is of dimension 1 and the regression sub-vi is asking for a 2D data. When i insert build array, it does not seem to solve the problem. So, how do i solve it?
0 Kudos
Message 1 of 3
(2,550 Views)
Hi Adeline,

if you are using a 1-D line fitting algortihm, then it should be asking for two 1-D arrays. One is the X-array, and the other the Y-Array. If you have a single set of data which is equidistant, beginning with zero, then you can "manufacture" an X-Array with a simple for-loop.

Since it sounde like you're plotting on an XY graph, you should already have X- and Y-Values in your code. Try connecting them both up as 1-D arrays. If this doesn't work, look for a 1-D line-fitting VI.

Hope this helps

Shane.
Using LV 6.1 and 8.2.1 on W2k (SP4) and WXP (SP2)
0 Kudos
Message 2 of 3
(2,545 Views)
Hi Adeline
Besides best fit, there are other solutions that can work fine with your data.
Try smoothing, you can download a vi from www.sciware.com.au (Savitzky-Golay smoothing filter for non-uniformly spaced data. )

Hope it helps
Alipio
---------------------------------------------------------
"Qod natura non dat, Salmantica non praestat"
---------------------------------------------------------
0 Kudos
Message 3 of 3
(2,534 Views)