STA312s19 Final Exam
This information applies only to the regular final exam, not the special deferred exam.
Time and location
The final exam will be on Tuesday April 16th in IB110, from 1-4 pm. Questions are like the quiz questions and the homework.
Format
The exam has 7 questions, most with parts a, b, c and so on. It is 15 pages including the cover sheet and my R input and output. You will write your answers on the question paper. There will be a separate
formula sheet. Keep a copy of the formula sheet handy as you prepare for the exam.
Homework
This course is mostly about the homework. The homework tells you what I want you to be able to do. Lecture material is only useful to the extent that it helps you do the homework. If the text and other readings are helpful too, that is great.
To study for the final, I recommend that you
- Do the sample questions presented in lecture; treat them as problems with solutions.
- Re-do the non-R parts of the homework.
- For each assignment, locate the corresponding lecture slides. This is mostly indicated on the course website.
- Look at the lecture slides and the homework problems together. Observe how most of the homework problems are asking you to use some concept or method from the lecture.
- Re-do the problems, referring to your earlier answers
- If you do not understand what a problem means or what it is asking you to do, this means you should find out. You are missing something, and it could be on the final exam.
- Using R, do something reasonable with the data sets described in the next section.
R
The R part of the final exam will be worth 25 marks out of 100. You will not write any R code on the exam, and you will not bring your printouts to the exam.. You will answer questions based on my analyses, using at least two of the following data sets.
- bfeed in the KMsurv package.
- retinopathy in the survival package.
- allograft in the KMsurv package.
- transplant in the survival package.
What should you do? In my opinion, more or less what you did on the R part of the homework. Also see the R lecture displays. There is more than one "right" answer, so beware of being persuaded by your friends. Tjink for yourself. The important thing is to become familiar with the data sets, try some analyses, and understand the results.
Some material, especially from the last part of the course, will appear only in the R part of the final exam, if it appears at all. There were no homework problems on the following topics, but you might see them in the R part of the final. Look at the R lectures, using the non-R lecture material as necessary for understanding. Try some of these methods on the final data sets.
- Residual plots
- Stratification
- Random effects (frailty)
- Competing risks
There will be nothing on time-dependent coefficients. Also, if I did not do something in the R lectures, it is very unlikely that I would do it on the final exam.
Office hours
- Tuesday April 9th, 11-1 (Jerry)
- Thursday April 11th, 11-1 (Jerry)
- Monday April 15th
- 11-1 (Jerry, in DH4009)
- 3-4 (Eman)
Quiz solutions
If you are in negotiation with Eman about your marks on one of the quizzes, that negotiation may continue. However, now that the answers are posted, there will be no new discussions of the marking. The reason should be obvious.
More suggestions and comments
- Bring a calculator with log and exponential functions. Make sure it's the natural log, not log base 10.
- Stating the null hypothesis: In this course, null hypotheses do not have greater than or less than signs. The significance level is always α = 0.05.
- Past final exams: Avoid them. This is a topics course, and earlier versions of STA312 were on different topics. As far as I know, survival analysis has never been offered before at U of T at the undergraduate level.
- Plain language conclusions: at least one question will ask you to state conclusions in "plain, non-statistical language." Here are some guidelines.
- Be guided by the 0.05 significance level, but never mention it. If you do, you get a zero even if what you say is correct.
- Any use of statistical vocabulary such as p-value, null hypothesis, significance etc. will get you a zero. Instead of saying ``controlling for," say ``allowing for," or ``correcting for," or ``taking into account." The phrase ``controlling for" will not get you a zero, but please avoid it when talking to non-statisticians.
- If a directional conclusion is posible, make it. Don't say ``Survival time was related to sex." Say ``Women tended to live longer."
- If a test is not significant , do not say there was no effect, or no difference. Avoid accepting the null hypothesis, or implying that you accept it. Say ``There was no evidence that surgery was related survival time," or ``These results do not provide evidence of a connection between marital status and time required to graduate," or something like that.
- For any explanatory variable that was not randomly assigned, avoid language that suggests influence, or causal connection. Say ``Patients with a health club memberships were at less risk for heart attack," not ``Exercise prevented heart attacks."
- Emphasis: In terms of point value, the emphasis is probably on the middle part of the course.
This document is licensed under a Creative Commons Attribution-ShareAlike 3.0 (or later) Unported License. The basketball data are protected by the Creative Commons license too.