Information Pertaining to the Final Exam
Basics
The official exam period is 7:30-10:15 PM on Thursday, June 26.
You are expected to take the exam during the official time slot.
Exceptions to this policy will rarely be made.
(Note: The official time slot for the exam may be changed.
For example, if there are too many class cancelations due to bad
weather, or for any other reason, the Provost may alter the exam
schedule.)
The exam is an open books and open notes exam.
You can use whatever printed or written material that you bring with you
to the exam. You cannot share books or notes during the exam.
You can use a calculator and/or computer during the exam if you wish to.
(Some may wish to use software such as Maple or Mathematica, in addition to R, however, I don't think that you should
have to use any software.)
You can connect to the internet to use Wolfram Alpha, a digital copy of the text, the course web site, or any of the
web sites associated with the text, but using it for any other
purpose will need prior approval from me. You cannot use the internet to communicate in any way with
another party. Also, cell phones should be kept out of your hands while you're taking the exam.
Extra Office Hours
In addition to my regularly scheduled office hours, I plan to hold
extra office hours in Room 1707 of the Nguyen Engineering Building during the following times:
- Wednesday, July 25, from 5:00 to 7:00 PM,
- Wednesday, July 25, from 8:00 to 10:00 PM.
Description of the Exam
The exam will consist of 15 parts, with each part being worth 2 points (since overall the exam will count 30 points). Some of the parts may be multiple
choice, true/false, or short answer questions, but others may require that you sketch a function, a decision tree, a dendrogram, or something of that sort.
(So the style of the exam will be very similar to the style of the quizzes.)
Eight of the parts will be strongly related to this semester's quizzes and homework exercises, and below are some very specific hints about these eight parts.
- Be prepared for something related to the 2nd question of Quiz 5.
- Be prepared for something related to Quiz 10. (Also see FIGURE 6.5 on p. 218 of ISL, and Exercise 4 on pp. 260-261 of ISL.)
- Be prepared to do something similar to Exercise 1 of HW 10, or Quiz 11.
- Be prepared to do something similar to Exercise 2 of HW 10, or Quiz 12.
- Be prepared to do something similar to Exercise 1 of HW 11.
- Be prepared for something related to 1 or more of the 1st 3 questions of Quiz 13.
- Be prepared to do something similar to Exercise 6 of HW 12 (but I may have you obtain the dissimilarity matrix from either a plot or a table
giving the data points to be clustered). In addition to single and complete linkage, also be prepared to deal with average linkage.
- Be prepared to do something similar to Exercise 7 of HW 12.
In addition to single and complete linkage, also be prepared to deal with average linkage.
Six of the parts will have you use your overall understanding of the performance characteristics of various classification and regression methods to come
up with a sensible answer to a multiple choice question.
- There will be three questions pertaining to a comparison of regression methods, related to the bias-variance trade-off.
- There will be a question pertaining to a comparison of classification methods, related to the bias-variance trade-off.
- There will be two questions based on scatter plots of data for a two-class classification task with two predictors. Based on your understanding
of the strengths and weaknesses of various classification methods, you are to indicate which method might be particularly good in one case, and which
method may perform poorly in another case.
One part will be based on something I discussed during the part of my Ch. 10 presentation related to principal components.
- There will be a question related to the loadings of principal components. (See pages 10-5 and 10-6 of the class notes.)