A distribution that is a "Mixture model" has a very similar definition as a "multimodal" distribution.

Wikipedia Says:

a multimodal distribution is a continuous probability distribution with two or more mode

Now to compare:

In statistics, a mixture model is a probabilistic model for representing the presence of subpopulations within an overall population, without requiring that an observed data set should identify the sub-population to which an individual observation belongs.

What is the difference between the two? They sound like they are the same thing!


To complement @matt's answer, you can also consider the beta distribution with $\alpha = .5$ and $\beta = .5$. It is illustrated by the red line in the figure below (copied from Wikipedia). As you can see, it is multimodal (viz., bimodal), but it isn't a mixture distribution:

enter image description here


Imagine a scenario where two distributions (e.g., two univariate normals) have the same mean, but different variances. In this example, they together form a unimodal distribution from a mixture of two different populations.

  • $\begingroup$ Ohh, nice! But in most cases, a multimodal distribution would be a mixture modal, right? $\endgroup$ – user46925 Feb 28 '16 at 20:46
  • $\begingroup$ @zero if you persist is spelling "model" as "modal" it's not surprising you're getting confused with "multimodal". (I fixed your title but you're also typing it in comments) $\endgroup$ – Glen_b -Reinstate Monica Feb 28 '16 at 23:02
  • $\begingroup$ lol - I'm fixing that. $\endgroup$ – user46925 Feb 28 '16 at 23:05

Your Answer

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