1
$\begingroup$

I am struggling analyzing the correlation between two variables in my experiments. It turns out that I now that when the SNR of the signal (the definition of the signal with respect to the noise) is high, the algorithm gives a better score. However, from the SNR-Score plot, I cannot see that relationship or at least it is not so evident.

What do you do when you have a correlation plot such as this?

enter image description here

I can see two clusters, and the cluster below is because some configuration of the experiment produced that results. but the rest seems to be a plateau not a linear regression model and the R2 is almost 0.

What kind of information could we extract from here?

Thanks for the help.

Improve this question
$\endgroup$
2
  • $\begingroup$ Please provide more details about your experiment and what you have plotted in this figure. $\endgroup$ Commented Apr 2, 2023 at 12:10
  • $\begingroup$ welll, my experiment is a computational neuroscience experiment where I run an algorithm to detect brain rhythms from the electrodes in the brain. I get the reference and output classes for the experiment and I perform a scoring process from the precision, recall, etc. Then I plot the Signal to noise ratio and the score, which is the information in the plot. $\endgroup$ Commented Apr 3, 2023 at 13:04

0

Reset to default

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.