I have a heuristic model of a physical process which is dependent on outcomes from random variables. The physical process approximated by the random number generator suggests what the distribution should be for that generator. For instance, a hypergeometric distribution to govern the introduction of a dispersed phase into a spray. The model takes inputs such as this and then processes those random draws and computes an outcome distribution of droplet sizes. I have experimental measurements of droplet size, and I want to adjust the parameters in the various distributions so that the model more closely predicts the outcome measured experimentally. What is this called? Is it point estimation? Should I have any expectation of robustness under, say changing surface tension? What should I be readying on this subject?

Thanks in advance!


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.