Here are the rankings for the second midterm.
1) Li'l Dictator
2) Grommett
3) Arf, Arf, I am a Dog!!
4) Pink Panther
5) Reptile
6) Razzmatazz
7) Faircloth D'Amato
8) Dilbert
9) Igby
10) Ginger
11) Knox
12) Mr. X
13) Fluffy
14) Colin Powell
15) Alison
16) Jet
17) World Class Dunce
18) Hillario
Here are some comments:
1) Overall, Gary and I are pleased with the results.
2) To the extent that you care more about letter grades than ranks, a
rough mapping would have the 1-7 as A, 8-10 as A-, 11-14 as B+, 15-16
as B, 17-18 as F. But, again, we keep track of ranks until the end, so
Li'l Dictator gets more points than Faircloth, for example.
3) The most problematic exams were 17 and 18. Those students should
contact us, either in person or via e-mail. As long as they did fine
on the first midterm, do fine on the final and/or do the homework
conscientiously, they will pass (that is, get a B) for the course.
4) Everyone should report their call signs to Tao (privately).
5) Anyone with knowledge of the person behind a given call sign should
keep that knowledge to himself.
6) The top 7 exams were all solid. Reasonable people could easily have
had a different ordering than we have here.
7) I will spend some time on Monday making general comments on the
exams and well as providing detailed comments on the two best exams,
both in terms of what they did well as well as what they did poorly.
8) Tao is working on written comments for all the exams.
9) I am available to meet in person with any student who would like to
discuss his/her exam with me.
10) One key mistake that several people made was to fail to recode the
incumbency code as something sensible. I will discuss this in class on
Monday. Short answer is that having an open seat encoded as 2 makes it
hard to interpret the regression coefficient as a meaningful estimate
of the incumbency advantage. What does a one unit change in the
incumbency variable mean in such a set up?
11) If you have not provided Tao with a PDF version of your exam, I
expect you to do so no later than class on Monday. Doing so is a part
of the exam process.
12) The "correct" answer seemed to be somewhere between 2% and 3%.
Congratulations on all the progress that you have made in the class. I
like to think that, taken as a whole, these exams demonstrate that you
are well on your way to being able to do publishable empirical
research in political science. Gary mentioned to a mutual friend of
ours (and assistant professor of political science) how far you had
gotten. His response was "Holy Sh*t!"
;-)
Dave
--
David Kane
Lecturer in Government
617-563-0122
dkane(a)latte.harvard.edu
Ryan Thomas Moore writes:
> Dave:
>
> I've been looking over the exams online, and it's definitely helpful to
> see the work of classmates.
I think so. I hope that other people take a look. You can learn a lot
by seeing how smart people tackle a problem that you have thought hard
about.
> My sincere thanks for providing these. How
> do I look at the two that don't appear to be Acrobat Reader-readable?
Those two files are in postscript. (Those two authors should provide a
pdf file to Tao for posting.) In the meantime, you can get Ghostview,
a free postscript viewer and view the files that way. Since so many
things are available in postscript on the web, it may be worth your
trouble to get this handy tool. This looks like the place to
start:
http://www.cs.wisc.edu/~ghost/
I would think that these tools would be available on the course1
server, perhaps /usr/X11R6/bin/gv is the trick . . .
Dave
> Ryan
>
> ------------------------------------------
> Ryan T. Moore ~ Government & Social Policy
> Ph.D. Candidate ~ Harvard University
>
> On Fri, 29 Nov 2002 dkane(a)latte.harvard.edu wrote:
>
> > Tao has kindly posted many of the midterms here.
> >
> > http://www.courses.fas.harvard.edu/~gov1000/Students_Midterms_Online/
> >
> > Although I have not finalized the grades yet, I have no problem in saying that
> > the midterms by "pink" and "dog" are both excellent.
> >
> > If, for some reason, you failed to provide Tao with a pdf file of your exam,
> > please do so at your earliest convenience.
> >
> > Dave
> >
> >
> > --
> > David Kane
> > Lecturer In Government
> > 617-563-0122
> > dkane(a)latte.harvard.edu
> > Please avoid sending me Word or PowerPoint attachments.
> > See http://www.fsf.org/philosophy/no-word-attachments.html
> > _______________________________________________
> > gov1000-list mailing list
> > gov1000-list(a)fas.harvard.edu
> > http://www.fas.harvard.edu/mailman/listinfo/gov1000-list
> >
>
--
David Kane
Lecturer in Government
617-563-0122
dkane(a)latte.harvard.edu
Thanks, Nirmala. This does help. But what exactly is this "pooled" data that
we rbind together? Is it *only* the data from 1920 and 1918, 1930 and
1928, ..., 1990 and 1988, or should we somehow be including the data from 1912,
1914, 1916, 1922, ..., 1992? If we should be including the 2, 4, 6 -ending
years (Ryan's earlier email implied that maybe we should), I have no idea how
to go about this.
Anna
> By "pooling" I think he means that we combine all the years rather than
> finding the incumbency effect for each election year. In other words,
> instead of running the regression within the loop that merges current year
> with lag year, rbind the merged data into a single dataframe within the
> loop and then run the regression after you have the "pooled" data for all
> the
> years. I hope this helps.....
>
> - Nirmala