1

I am currently working with a dataset of a sensor detecting Strontium-90 beta minus emission. I have succesfully built an histogram of energies and, as I would expect, i get a "Landau-like" spectrum (typical of energy decay in a thin absorber). Now i'd like to overlay a the Landau curve that best fits my data (the same way it's frequently done with a normal distribution); however I can't find any useful resource online, neither for the landau itself nor for the moyal function.

Any ideas?

edit: I both need to get the parameters of the landau that best fits and to plot it over my histogram. The moyal function is an approximation of the landau with a definite formula (instead of a PDF).

Jacopo Altieri
  • 15
  • 6
  • Is your question how to overlay the best-fit Lanau distribution on the observed histogram, how to obtain the parameters of the best-fit Landau distribution, or both? What is "the moyal function"? – Limey Jul 05 '21 at 15:30
  • It may be hard, but if you have the parameters you could try to write the [PDF](https://en.wikipedia.org/wiki/Landau_distribution) as a function and plot it. For complex integration, check [this question](https://stackoverflow.com/questions/20542767/coding-complex-integration-and-limits-in-r/20553185), but I don't think it is really necessary, there probably is a known way of writing the integral limits with real numbers. – Eduardo Freire Mangabeira Jul 05 '21 at 15:38
  • I didn't have any difficulty finding a package that has a (p,d,r)-Landau distribution family. Maybe you should be describing your search methods and then asking for further ideas. I'm not sure this is the right place to be asking that question however. – IRTFM Jul 05 '21 at 16:57
  • Without data and code that shows some effort, I'm voting to close. My close vote can be reversed if those issues are addressed. See https://meta.stackoverflow.com/questions/261592/how-much-research-effort-is-expected-of-stack-overflow-users and https://stackoverflow.com/help/how-to-ask – IRTFM Jul 05 '21 at 20:07
  • It will be extremely challenging to answer your question without **1)** the code you've tried thus far and **2)** at least a sample of your data. Please [edit] your question with the output of `dput(data)` or `dput(head(data))` if your data is very large. See [How to make a great R reproducible example](https://stackoverflow.com/a/5963610/) for more. – Ian Campbell Jul 06 '21 at 04:17

0 Answers0