I have a dataset where I highly suspect some correlation by two variables, based on my understanding of the problem. I would have a linear correlation (sort of SVD decomposition or a plane such as $y=mx+p$ for the main axis separation) of these variables. Assuming that I find the right separation, I would expect the principal axis to follow a gaussian distribution (high noise) and the secondary axis to follow and decreasing exponential probability (or maybe a poisson distribution with $\lambda$ close to 1).

My question is: how to test that and how would I extract the key parameters ($\lambda$ for exponential distribution, $\mu$ and $\sigma$ for the gaussian distribution and more importantly, the $m$ and $p$ for the $y=mx+p$ plane separation?)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.