|
Pages: [1]
|
 |
|
Author
|
Topic: linear correlation coefficient is strange (Read 1174 times)
|
SteveRock
Newbie
Posts: 1
|
I have just installed the beta version and found it to work just fine (Ubuntu 8.04) with a large force plate. However, in curve fitting, with the sensor zeroed out and no force applied, the data is very straight and limited to the noise of the system, but the correlation coefficient is nowhere close to 1. It's closer to -0.05. This is obviously not correct.
|
|
|
|
|
Logged
|
|
|
|
gastineau
Vernier Specialist
Full Member
Posts: 122
|
Without seeing your data, I cannot say for sure. If you like, please send the cmbl file to info@vernier.com and we'll look at it.
However, note that a data set with a zero slope will have a zero correlation.
Do you see the expected correlation coefficient with non-zero sloped data?
--John Gastineau, VS&T
|
|
|
|
|
Logged
|
|
|
|
Chadmama
Newbie
Posts: 1
|
Hi guys
7 Pearson's linear correlation coefficient, rxy, between two variables X and Y ... of construing the meaning of Pearson's correlation develops in a strange way.Y is linear, you should use the Pearson correlation coefficient discussed below. ... For some strange reason, the value of the computed t is not generally.
Thanks
lits gonflables - brumisateur de terrasse
|
|
|
|
|
Logged
|
|
|
|
Garth
Global Moderator
Full Member
Posts: 169
|
I'm sorry, I don't understand your last post -- maybe something got left out?
Thanks
-Garth
|
|
|
|
|
Logged
|
|
|
|
|
Pages: [1]
|
|
|
|
|
|
