1
$\begingroup$

I want to know the percentage of individuals in the "low-squeak" and "high-squeak" groups with uncertainties. How do I calculate it given the following bimodal distribution?

For example, I need to get the result in the following form:

  • "Low-squeak": 20±5%,
  • "High-squeak": 80±5%.

Number of penguin squeaks per hour

$\endgroup$
2
$\begingroup$

Look into Gaussian mixture models.
You basically assume an existence of 2 sub populations in your data.
Fit a model with relevant parameters per each of the populations.
Then using the parameters estimated, you can get estimation of the ratio of each sub population in all of the population.

This similar question has a more detailed answer.

$\endgroup$
1
  • $\begingroup$ Thanks, when fitting two gaussians M=pϕ1+(1−p)ϕ2, will it be possible not only to get the value but also the uncertainty for the mixing proportion p? $\endgroup$
    – Evgenii
    Nov 25 '19 at 8:30

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.