Exercises

Here is a series of exercises. Answers to all the exercises are given in the Jupyter Answers_to_Exercises_Chap5.ipynb notebook in the GitHub repository:

1. For the MAP estimation code example in the text, we used the scipy.optimize.minimize function to do the optimization of the log-posterior. The minimize function has the option for the user to supply a callable function that calculates the gradient of the objective function with respect to the objective function parameters. Work out on paper the gradient of the log-posterior and implement a function that returns the gradient of the log-posterior. Re-run the MAP estimation process using scipy.optimize.minimize, but when you pass in your log-posterior gradient function, you’ll need to look at the online documentation for the scipy.optimize.minimize function to see how your callable gradient function should be passed in.
2. The Data/coffee_or_tea.csv file in the GitHub repository contains two columns of data,...