The purpose of the paper is for you to show that you can use the various R techniques introduced in the course. The video goes through the sort of structure it should have.

I have put up a short paper called “tryout. Rmd”. This is to check that R can find your data and that you can turn the document into a PDF. You should run this immediately and if you have problems contact me so that we can fix whatever is wrong as soon as possible.

Basically, there should be an introduction first that gives a short description of what you are doing, and what you have found. It should also include some references that are roughly in the area, just to show that you understand how to
make a bib file. These just need to be something along the lines of “Studies include…”

Next, there should be a summary of the data, discussing notable features. You should particularly address whether variables should be treated as logs (percent-age changes) or levels (changes are in original units).

The core of the paper is the regression section. You should run a regression starting with the main explanatory variable and add others as controls. Use the model summary to make a table and model plot to plot the coefficients. You should then give a discussion of what you find: this is a really important part.

Next, you can include any fancier techniques that you want to use such as splines, classification trees, etc. If you want you can put in a short conclusions section.