Note: I have posted last year’s final exam. I don’t have a set of grading guidelines for this one typed out, but I’m happy to discuss any of the problems in office hours.
On Monday, we will aim to set you up for the second homework problem this week by covering:
- the limitations of parametric probability models.
- bootstrap resampling for modeling portfolios with many assets.
For doing this in class, please download the script portfolio.R. Depending on how much time is available, we may start on Chapter 16.
Then on Wednesday, we finish up the semester with one last topic: logistic regression. For class, please download:
- challenger.R from the R Scripts tab
- challenger.csv from the Data tab
In class on Wednesday, we will also work on the last problem from this week’s homework, on conditional probabilities in breast-cancer screening.
Reading
For Monday, you’ll want to have read my short (2.5 page) set of summary notes on bootstrap resampling.
For Wednesday, read through page 305 of Chapter 16. You can safely stop once you reach the section entitled “Advanced topic: estimating the parameters of the logistic regression model.” You are not responsible for anything beyond this section.
Software
Last walkthrough of the semester! By Wednesday, please complete the R walkthrough on logistic regression.
Exercises
There are no new exercises. Exercises 9, assigned last week, are due by 5 PM on the last day of the semester: Friday, May 4, 2018. You may submit them as an electronic copy – PDF only, please – to statdropbox@gmail.com (same e-mail as for projects).