linear regression correlation coefficient

[BB_Herman]

Does anyone have a vi that computes the linear regression correlation coefficient (R^2)?

[VipersView]

This might help.

[GGivan]

Try this VI.

[altenbach]

The solution with the minimal amount of LabVIEW coding takes advantage of the fact that the correlation coefficient can be obtained from:

r^2 = bb'

i.e. the product of the slope b and the slope b' obtained from swapping the x and y input arrays.

See attached image.

[gbaby]

I only have the LabView Base development package, is there any way for me to make an easy work-around for finding the correlation coefficient or will I have to implement the equation?

[altenbach]

Implementing the equation seems like an easy workaround. 😄

[gbaby]

I know this thread is ten years old but I'm still going to post the subVI i made, it will work even for those with the base development package. Hope this proves useful for somebody out there.

[GerdW]

Hi gbaby,

yes, the thread is VERY old.
10 years later the function palettes have changed a lot and now contains functions like that (atleast in FDS)...

[gbaby]

I only have the basic development package, trust me I know that the Full and Professiona have all kinds of toys built in that I have to either build myself or find in decade-old threads. I just posted mine in case somebody is in my situation.

[altenbach]

---

@gbaby wrote:

I know this thread is ten years old but I'm still going to post the subVI i made, it will work even for those with the base development package. Hope this proves useful for somebody out there.

---

Thanks! Actually, looks very similar to the one posted by greg over 10 years ago. 😮

You can eliminate the FOR loops (might perform better by taking better advantage of SSE). After the FOR loops are removed, there are a few common sub-expressions that you can merge for even better performance. No big deal, though. 😉