Instructions
When you have completed the assignment, knit the document into a PDF file, and upload _both_ the .pdf and .Rmd files to Canvas.
Note that you must have LaTeX installed in order to knit the equations below. If you do not have it installed, simply delete the questions below.
Question 1
In this assignment, you will be required to find a set of data to run regression on. This data set should be financial in nature, and of a type that will work with the models we have discussed this semester (hint: we didn’t look at time series) You may not use any of the data sets in the ISLR package that we have been looking at all semester. Your data set that you choose should have both qualitative and quantitative variables. (or has variables that you can transform)
Provide a description of the data below, where you obtained it, what the variable names are and what it is describing.
Question 2
Pick a quantitative variable and fit at least four different models in order to predict that variable using the other predictors. Determine which of the models is the best fit. You will need to provide strong reason why the particular model you chose is the best one. You will need to confirm the model you have selected provides the best fit and that you have obtained the best version of that particular model (i.e. subset selection or validation for example). You need to convince the grader that you have chosen the best model.
Question 3
Do the same approach as in question 2, but this time for a qualitative variable.
Question 4
For the Boston data set, fit a tree trying to predict crime (crim) based on all of the other variables. This should be the best tree that you can fit (you should try bumping, bagging, and boosting to ensure this).