Midterm Exam

Warning

The midterm exam will be in class on Monday October 17.

Exam Information

You may not have anything with you for the exam (no notes, etc) except a calculator. I write questions such that you can get a perfect score without a calculator, and answers should typically be simple whole numbers. However, I understand that if nothing else, calculators are moral support and you can use them. I will provide simple calculators if you need to borrow one, as well as extra paper.

I write the exam so that most students can complete it in less than the required time, but you will have the whole class period, plus a few minutes between classes. Questions draw from concepts in the slides and whatever we discuss in class, no other outside knowledge is needed.

You must show your work for all problems. On all exam questions, I give points for partial credit. The more of your thought process you show (if you are unsure), the more points I am able to give. Both correct answers with no work shown, or blank answers will not receive full points.

If you have any approved testing accommodations, or know in advance you must be absent, please confirm with me ASAP and we will make arrangements

Study Tools

My Advice

Make sure you do all of the homework problems and learn from the answer keys to the homeworks, as well as the in-class practice problems. While some of the questions should be novel applications, conceptual questions on homeworks will get you in the right headspace to think about answering a question on an exam.

Things Worth Knowing/Memorizing

  • The difference between exogenous and endogenous variables/models
  • How OLS estimators are chosen (minimize SSR)
  • The four assumptions made about the error term, and which one is most important, and why
  • What \(R^2\) means, in English, and the methods of calculating it
  • What \(SER\) means, in English
  • What homoskedasticity and heteroskedasticity mean, in English
  • How to read a regression table and various forms of regression outputs from R
  • Interpreting what \(\hat{\beta}_0\) and \(\hat{\beta}_1\) are in terms of a graph and in terms of a question