9 Jan
2003
9 Jan
'03
2:09 a.m.
There's an article by GK (just Gary, not Gelman too) in the American
Journal of Political Science (30:3), entitled "How Not to Lie with
Statistics" that's pretty useful...it's on JSTOR.
Olivia.
9 Jan
9 Jan
2:31 a.m.
I think "How Not to Lie With Statistics" is on the Gov 1000 course
website, too, if that's quicker for people to look up. (It was an
assigned reading for class.) And I agree with Olivia, it's pretty
useful.
Anna
2:17 p.m.
<ahem!>
I knew that article sounded familiar...
Olivia.
On Thu, 9 Jan 2003, Anna Lorien Nelson wrote:
I think "How Not to Lie With Statistics" is
on the Gov 1000 course
website, too, if that's quicker for people to look up. (It was an
assigned reading for class.) And I agree with Olivia, it's pretty
useful.
Anna
_______________________________________________
gov1000-list mailing list
gov1000-list(a)fas.harvard.edu
http://www.fas.harvard.edu/mailman/listinfo/gov1000-list
2:35 a.m.
New subject: removing dataset points
A quick question :
does somebody know an efficient way to remove an outlier as seen on a
residual plot? (it can be tricky if the lm function uses only a subset
of the initial data.. the observation number on the residual plot refers
then to the subset, not to initial dataset)
Thanks,
Stan
8:54 p.m.
New subject: removing dataset points
Stanislav Markus writes:
A quick question :
does somebody know an efficient way to remove an outlier as seen on a
residual plot? (it can be tricky if the lm function uses only a subset
of the initial data.. the observation number on the residual plot refers
then to the subset, not to initial dataset)
Have you checked out identify()? You can use the "label" argument to
get all the info about a particular point that you could want. I think
that the Modern Applied Statistics with S Chapter 1 that we read has
some examples (don't have it with me now).
Dave
Thanks,
Stan
_______________________________________________
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
7800
days inactive
7801
days old
gov1000-list@lists.fas.harvard.edu
5 comments
5 participants
participants (5)
-
Anna Lorien Nelson -
Dave Kane -
Olivia Lau -
Stanislav Markus -
Tao Li