Take-home Content (100 points)

As explained in the syllabus, the exam consists of two components. The first is a take-home exam that will be distributed by noon on Monday, October 24th. To access the exam, you will run the notebook00.Rmd file; that will download the file exam02.Rmd, which contains the exam questions, and any associated datasets. Answer the questions as you have done in the class notebooks, knit the notebook, and bring your printed solutions to class on Wednesday, October 26th. You may use any static resources for the exam but cannot discuss the questions with anyone else.

The questions will most closely resemble Notebooks 8, 12, 13, and 14. Since it is open book, all of the material we have coverd in class through the “14. Tidy Models” notes (whether it be in the notes, slides, or notebooks) is fair game for the exam. Pay close attention to the code formating rules in the first and second set of notes. You will lose points for formatting errors on the take-home exam.

In-Class Content (100 points)

The in-class exam will take place on October 26th. It is a closed book exam that will be done entirely on paper. There will be ten questions. Unlike the first exam, the exam does not involve writing any R code. In the exam, I will give you several small datasets and ask you do to some subset of the following with each of them:

  1. Write down the output consisting of joining two of the tables.
  2. Write down the output of pivoting a table wider or longer.
  3. Identify the candidate keys in a table.
  4. Categorize the most strict form of data normalization (1NF, 2NF, or 3NF) that a table is currently in.
  5. Rewrite a dataset in a more normalized way.
  6. Rewrite a dataset that does not conform to our rules for data organization.

There will also be one question that asks you to list the four actions we discuss as being part of the Data Feminism.