Discussion of Maximum Likelihood Estimation
- What is the goal of estimating a parameter? Why is this something that we are interested in as data scientists?
- In your own words, describe how the method of maximum likelihood is used to estimate the unknown parameters.
- Why does a likelihood function have a \(\Pi\) (product operator) within it?
- Is it possible to estimate using maximum likelihood without writing down a model for the data?
- What happens if your model for the data is wrong? Are your estimates for the parameters “incorrect”? Or, are they “correct” within the context of the model that you’ve written down?