Just a quick note to bring a resolution to this list thread, and inform the list of
feature additions, the plot.ci() now has added capabilities. If you have a range of some
independent variable, x, in addition to plotting expected values and predicted values
across the range of x, you can now specify another range for another variable, say x1, and
plot two sets of expected variables against each other, or plot the distribution of the
first differences between x and x1, as you move over the range. These features are
currently in the Beta distribution, and the RDocs for that distribution, and will be on
CRAN and added to the manual in a weeks time.
James
--
James Honaker, Senior Research Scientist
//// Institute for Quantitative Social Science, Harvard University
________________________________________
From: zelig-bounces(a)lists.gking.harvard.edu [zelig-bounces(a)lists.gking.harvard.edu] on
behalf of Honaker, James [jhonaker(a)iq.harvard.edu]
Sent: Tuesday, March 05, 2013 2:26 PM
To: Tingley, Dustin; zelig(a)lists.gking.harvard.edu
Subject: Re: [zelig] plot.ci problems
Dustin,
I'm not certain from your message precisely what you are attempting before this
running command, so ignore one of the two answers I give below. If you are rerunning a
piece of code, from start to finish, in Zelig 4, the plot.ci() function now has some
added capability, but you to specify an additional argument. It is now possible to have
multiple variables moving simultaneously across ranges, but it is necessary to specify
which variable you want on the X-axis (even if only one variable is moving).
So you might change your command to: > plot.ci(s.out1, var="age")
if for example the variable "age" was moving across some range in Zelig's
sim() function and you wanted that on the X-axis.
If instead of rerunning code, you are loading a previously saved zelig result object (from
say an Rdata workspace) and simply attempting to rerun the graphs on the results, then
there will be an issue, because the Zelig result object has changed substantially with
Zelig 4 to deal with S4 classes and methods in R. You would not be able to run Zelig4
functions on result objects from Zelig 3.x and earlier. Contact me and I can give you
directions for installing our archive of Zelig 3.5 if it is the case that you want to
revisit saved result objects from earlier Zelig packages.
Let me know if that just raises more questions, or if any further issues emerge with the
new plot.ci() function,
James.
--
James Honaker, Senior Research Scientist
//// Institute for Quantitative Social Science, Harvard University
________________________________________
From: zelig-bounces(a)lists.gking.harvard.edu [zelig-bounces(a)lists.gking.harvard.edu] On
Behalf Of dustin tingley [dtingley(a)gov.harvard.edu]
Sent: Tuesday, March 05, 2013 1:49 PM
To: zelig(a)lists.gking.harvard.edu
Subject: [zelig] plot.ci problems
Hi-
I went to change some graphs I produced earlier with Zelig.
I can still run summary on my zelig object, but when I run plot.ci<http://plot.ci> I
get
plot.ci<http://plot.ci>(s.out1)
NULL
This was not a problem in the last version of Zelig I had (3.5ish, I think).
Can someone help me?
best,
Dustin
Dustin Tingley
Government Department
Harvard University
http://scholar.harvard.edu/dtingley
Director, Program on Experience Based Learning in the Social Sciences
http://projects.iq.harvard.edu/peblss/
Contribute to the Research Reservoir:
http://projects.iq.harvard.edu/undergradscholars/pages/research-resources
-
--
Zelig Mailing List, served by HUIT
Send messages: zelig(a)lists.gking.harvard.edu
[un]subscribe Options:
http://lists.gking.harvard.edu/mailman/listinfo/zelig
Zelig program information:
http://gking.harvard.edu/zelig/
Zelig mailing list
Zelig(a)lists.gking.harvard.edu
To unsubscribe from this list or get other information:
https://lists.gking.harvard.edu/mailman/listinfo/zelig