Has anybody figured out how to put in an abline (i.e. flat line or 45 degree
line) in lattice graphs? using abline(0,1) doesn't seem to do anything.
Thanks,
Phillip.
-------------------------------------------------
Phillip Y. Lipscy
Perkins Hall Room #129
35 Oxford Street
Cambridge, MA 02138
(617)493-4893
lipscy(a)fas.harvard.edu
First Year Student, Ph.D. Program
Harvard University, FAS, Department of Government
-------------------------------------------------
Anybody have any ideas about how to expand the font size of the x/y axes and
other labels when going from an R figure to a postscript file? I imported my
lattice graph into my tex document, and you need a magnifying lense to read the
labels (esp. the category labels). This also seemed to be a problem with the ps
files we made before, but it's more severe now that we're trying to fit multiple
graphs into a single figure.
Thanks,
Phillip.
-------------------------------------------------
Phillip Y. Lipscy
Perkins Hall Room #129
35 Oxford Street
Cambridge, MA 02138
(617)493-4893
lipscy(a)fas.harvard.edu
First Year Student, Ph.D. Program
Harvard University, FAS, Department of Government
-------------------------------------------------
Tao Li
--------------
www.people.fas.harvard.edu/~li7
---------- Forwarded message ----------
Date: Sat, 28 Dec 2002 21:35:07 -0500 (EST)
From: Gary King <king(a)harvard.edu>
To: Phillip Y. Lipscy <lipscy(a)fas.harvard.edu>
Cc: Tao Li <li7(a)fas.harvard.edu>, dkane(a)latte.harvard.edu
Subject: Re: data source
data availablity, and to some small extent simplicity of data types.
Gary
On Sat, 28 Dec 2002, Phillip Y. Lipscy wrote:
> Quick question about the final exam data: were the 14 states selected through a
> random process or deliberately due to issues such as limited data availability?
>
> The answer to this question would seem to have implications for how general our
> conclusions can be and whether there would be systemic bias.
>
> Thanks,
> Phillip.
>
> -------------------------------------------------
> Phillip Y. Lipscy
> Perkins Hall Room #129
> 35 Oxford Street
> Cambridge, MA 02138
> (617)493-4893
> lipscy(a)fas.harvard.edu
>
> First Year Student, Ph.D. Program
> Harvard University, FAS, Department of Government
> -------------------------------------------------
>
>
>
>
>
Dear all,
Does anybody know how to change the background color for the lattice output? I
get an ugly brownish color by default and it's pretty gross. Also, any advice
on how to change the labels for the multiple plots/histograms when they're
produced? I've tried several things but the labels on each plot are always the
same and something generic like "data.frame$column." How do you change them to
something like "California" "Colorado" or "1920" "1930" etc.?
BTW, can we expect an answer key for the Lattice Problem from HW8? The website
is somewhat helpful but assumes a lot of technical know-how that we don't have.
Thanks,
Phillip.
-------------------------------------------------
Phillip Y. Lipscy
Perkins Hall Room #129
35 Oxford Street
Cambridge, MA 02138
(617)493-4893
lipscy(a)fas.harvard.edu
First Year Student, Ph.D. Program
Harvard University, FAS, Department of Government
-------------------------------------------------
---------- Forwarded message ----------
Date: Sun, 22 Dec 2002 08:21:24 -0500 (EST)
From: Gary King <king(a)harvard.edu>
To: Nirmala Ravishankar <ravishan(a)fas.harvard.edu>
Cc: Dave Kane <dkane(a)latte.harvard.edu>, Tao Li <li7(a)fas.harvard.edu>
Subject: Re: "Lost" question from problem set 8
It would be good if you can figure it out (I'd look at the examples to
do so), but at this point if you can't please don't worry about it.
Gary
On Sun, 22 Dec 2002, Nirmala Ravishankar wrote:
> Dear Dave,
>
> Given that we never formally did Lattice in class, it would be very
> helpful if you could provide a solution to the problem you
> added to assignment 8. I was able to do the basic bar graph using
> lattice, but nothing as sophisticated as a panel of histograms or a
> panel of bar graphs for northern, southern and western states etc. And the
> help menu is written in R jargon -- I cannot tell a shingle from a
> jitter! How much time do you want us to spend figuring out lattice?
>
> - Nirmala
>
>
>
>
>
>
>
think about the variance of linear functions...
Gary
On Fri, 20 Dec 2002, Yevgeniy Kirpichevsky wrote:
> Dear Gary, Dave, and Tao,
>
> Below is a dataframe, which
> gives a value of the incumbency coefficient for each year with the
> corresponding 95 % confidence interval. the t.test on the psi values
> gives the 95%CI of .026 to .063, which is pretty big since it's based on
> only 7 datapoints. But it seems like it could be much smaller, since for
> each year the number of datapoints is largy - about 100. this is
> reflected in the confidence intervals for each individual psi. Would it
> be terribly wrong then to construct a 95% interval for the mean psi by
> taking the mean of CI boundaries for each year?? it would be (.033, .056)
> - smaller than (.026, .063).
> Thank you
>
> -yev
>
>
>
> > psi
> year psi ci.low ci.high
> 1 1970 0.02075644 0.01197663 0.02953625
> 5 1974 0.02153942 0.01094814 0.03213070
> 7 1976 0.02923420 0.01901227 0.03945612
> 9 1978 0.05216359 0.04059904 0.06372815
> 11 1980 0.05336988 0.04182857 0.06491120
> 15 1984 0.06943829 0.05631771 0.08255886
> 17 1986 0.06365428 0.04991084 0.07739773
>
> > mean(psi1$ci.low)
> [1] 0.03294189
> > mean(psi1$ci.high)
> [1] 0.05567414
>
> > t.test(psi$psi)
>
> One Sample t-test
>
> data: psi$psi
> t = 5.8013, df = 6, p-value = 0.00115
> alternative hypothesis: true mean is not equal to 0
> 95 percent confidence interval:
> 0.02561964 0.06299639
> sample estimates:
> mean of x
> 0.04430801
>
Note that some people (read: Mostly me and Tiffany once) have sent some
messages to the old mailing list by mistake. They go there but they don't get
sent out. You can see them at:
http://www.fas.harvard.edu/pipermail/gov1760-l/2002-November/date.html#start
and look at the last 5 messages.
If you have advice for Tiffany or an interest in lunch with me or questions
about the paper, then please respond.
Dave
--
David Kane
Lecturer In Government
617-563-0122
dkane(a)latte.harvard.edu
Hope everyone is having a happy holiday season...
... because my computer sure isn't!
Does anyone know of a good VNC Viewer application for Mac OS X? (e.g., the one
used to make the help pages?) Please don't refer me to the link with the list
of all the viewers, because I've already installed four of them and they aren't
what we need for Gov 1000.
thanks,
Olivia
Stanislav Markus writes:
> Dave, Gary, Tao,
>
> We are asked to do both matching and regression. Should we allocate our
> energy equally between the two, say 5 pages each, or should we focus
> more on regression, and do matching just to compare results?
Both matching and regression are equally important.
> Also, we've never talked in-depth about matching in non-experimental
> settings.
I tried to! Recall the time we spent of the treatment effect of "being talked
to on the phone". Although it was true that being assigned to the treatment of
"being on the call list" was done randomly (more or less), the treatment
assignment of actually talking to someone was *not* random. The potential
voters who were talked to were very different from ones that were not talked
to. That is why we had to match.
> What I wonder about is correct verbiage and conceptual
> clarity: is it meaningful e.g. to talk about incumbency as "treatment",
Yes. If you want to talk about the causal effect of incumbency than,
conceptually at least, it must be a treatment.
> or about "an assignment mechanism" since nobody really assigns
> treatments here..?
As in the case of the "getting talked to" treatment, nature (or, rather, some
force other than experiment) does the assignment.
If this is not clear to you, I urge you to take a look at the Holland and Rubin
readings that I suggested.
Dave
> Thank you,
> Stan
>
>
--
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