Applied Statistics PhD Comprehensive Question #1

2008-08-11 at 12:22 am 6 comments

PhD students in the Dept. of Statistics at the University of Toronto normally write three comprehensive exams at the end of their first year, in Probability, Theoretical Statistics, and Applied Statistics. Below is a question I set for the 2008 exam in Applied Statistics. It may be an interesting exercise for others too. It should in theory be doable by someone with just a good introductory undergraduate course in statistics, including multiple regression. However, many PhD students had difficulty with it, so I wouldn’t say it’s easy.

The question is here. I’ll post my answer in a week or so. I’ll also post a question from 2007 sometime.

Update: Here is the post with the answers.


Entry filed under: Statistics, Statistics - Nontechnical.

University College, University of Toronto The Harmonic Mean of the Likelihood: Worst Monte Carlo Method Ever

6 Comments Add your own

  • 1. Hans  |  2008-08-20 at 6:58 pm

    When you say that many PhD students have difficulty, do you mean that they give incorrect/incomplete answers or that they have trouble simply getting their heads around the questions and forming any answer at all? Also, is there a time limit on these questions or can they sit in the room and think about it for several hours?

  • 2. radfordneal  |  2008-08-20 at 8:07 pm

    I don’t want to go into details about the students who answered this particular question. But in general, I think questions like these are hard for some students for several reasons. They may not be used to thinking about issues like “which of these analyses is better?” They may not have a clear understanding of the justifications for use of various procedures. They may lack “common sense”. A lot of these problems may stem from deficiencies in earlier education, which may have emphasized “cook book” approaches. Of course, all the recent texts say they’re teaching concepts, not cook book procedures, but saying and doing are different things.

    For this particular question, some of the parts are fairly straightforward, and most students did well on those parts. The question about whether Fred or Mary’s analysis is better, with the three views on this, was the most difficult. This exam was time limited, but the time limit was pretty generous.

  • 3. ZBicyclist  |  2008-08-20 at 11:53 pm

    I like the questions. I particularly like the second one (caffeine), with the three views.

    Of course, you could flip it around (Fred’s analysis shows no difference, Mary’s does).

    A further question would then become: would you pick the same philosophical answer under both conditions?

  • 4. David  |  2008-09-17 at 4:06 pm

    very nice set of questions and well-written clear answers. these will provide very good preparation for your students.

  • 5. Horse  |  2008-12-23 at 2:56 pm

    Great, Dr. Radford,
    Could you explain the format of the PHD comprehensive exam, eg.
    How many questions it has, How to prepare it?

  • 6. Radford Neal  |  2008-12-23 at 6:49 pm

    If you are wondering about the comprehensive exam for a PhD in Statistics at the University of Toronto, you should look at the information here. This may be roughly typical of such exams, but I expect there is considerable variation from university to university.


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

Trackback this post  |  Subscribe to the comments via RSS Feed


August 2008
    Sep »

Most Recent Posts