The second Quiz (see dates page) will cover material from Module 8 (Univariate EDA – Categorical), Module 9 (Normal Distributions), Module 10 (Bivariate EDA – Categorical), Module 11 (Bivariate EDA – Quantitative), and Module 12 (Linear Regression). The quiz is primarily application questions but several short answer essay questions will also be asked. The only R work that you will need to do is related to using distrib() for normal distribution calculations. The portion of the R cheat sheet related to distrib() will be provided on the quiz. Any material in the module readings and videos (specifically questions on the preparation guides), exercises (most completed in class), or review exercises may be on the quiz.

  • [8%] Two short answer essay (2-4 sentences) questions all from the Module 12 (Linear Regression) preparation guide.
  • [4%] Perform a univariate EDA for categorical data … like this (but you won’t have to do the R work, just interpret the results of a frequency table, percentage table, or bar chart) in Module 8 (Univariate EDA – Categorical).
  • [22%] Normal distribution calculation questions (that will use distrib()) … like this (among many others) in Module 9 (Normal Distributions).
  • [16%] Calculations from a two-way frequency table (row-, column-, and table-percentages as necessary) … like this (and others, but you won’t have to do the R work) in Module 10 (Bivariate EDA – Categorical).
  • [20%] Perform a bivariate EDA for quantitative data … like this (and others, but you won’t have to do the R work) in Module 11 (Bivariate EDA – Quantitative).
  • [30%] Answer the twelve usual questions for linear regression … like this (among others) in Module 12 (Linear Regression). Note that one thing different about this quiz question is that I will provide two scatterplots with best fit lines and equations. The two plots will have the variables reversed on the axes such that you will have to choose the proper plot to use based on determining the response and explanatory variables in the question.

I strongly believe that the best way to prepare for this quiz is by …

  1. Reviewing what you did on the exercises. I would carefully compare your answers to the answer keys that are now available. Also pay close attention to the “notes” that I have placed in yellow boxes in the answer keys.
  2. Practice more exercises, either in the “more as time permits” links for some modules or in the review exercises (many of these are old test questions) for all modules. Focus on questions that are similar to the ones linked to in the list above.
  3. Study your module preparation guide notes carefully. Augment them by rereading portions of the reading where your notes are poor.
  4. Start practicing early so that if you have questions you can get help from me or from the tutors (who have tutor hours on the Thursday before the quiz).

The quiz is closed book, closed notes, etc. You should bring a calculator and you MUST use a pencil. You will need to logon to a Northland computer (no personal computers will be allowed) to use distrib() for the normal distribution questions. You should only open RStudio and no scripts should be open (i.e., make sure you close all of your scripts in RStudio prior to coming to the quiz). Computer use will be monitored during the quiz. Quizzes written in red ink will not be accepted and will earn a zero. The quiz will begin promptly at 0800 for the first section and 1000 for the second section and must be turned in within 1 hour and 50 minutes. Please take care of your personal needs before the quiz so that you do not need to leave class during the quiz (if, for some reason, you do need to leave the room, make sure to leave your phone and other devices in the room and let me know that you are leaving the room).

Please let me know if you have any questions about this quiz.