Both handle a wide range of models, although there are some differences. Stargazer can convert multinom, for example, both convert lmer.
Sep 28
Here’s the gated poq article:
http://poq.oxfordjournals.org/content/early/2012/09/15/poq.nfs038.full.pdf
and some “international” coverage:
http://www.slate.fr/monde/62445/republicain-democrate-couple-possible
http://www.motherjones.com/kevin-drum/2012/09/you-hate-me-you-really-hate-me
http://jezebel.com/5947176/republicans-and-democrats-are-less-tolerant-of-interparty-marriage
Apr 22
Edits were sent for proofing to POQ. Hence, In Press.
Abstract
The current debate over the extent of polarization among the American mass public focuses on the extent to which policy attitudes have moved. While “maximalists” claim that partisans’ views on policies have become more extreme over time (Abramowitz 2010), “minimalists” (Fiorina and Abrams 2009) respond that the majority of Americans remain centrist, and that what little centrifugal movement has occurred reflects sorting, i.e., the increased association between partisanship and ideology. We argue in favor of an alternative definition of polarization, based on the classic concept of social distance (Bogardus 1947). Using data from a variety of sources, we demonstrate that both Republicans and Democrats increasingly dislike, even loathe their opponents. We also find that partisan affect is only weakly founded in policy attitudes; thus movement in policy attitudes may not explain affective polarization. The more plausible account lies in the nature of political campaigns; exposure to messages attacking the out-group confirms partisans’ biased views of their opponents.
Apr 12
My friend and frequent collaborator Ariel Malka, a professor of psychology at Yeshiva University, just wrote an op-ed at Fox News.com:
Apr 11
Headed to MPSA to present papers on these panels:
| 28-27 Elite Influence on Public Opinion |
| 1-18 Comparative Perspectives on Immigrants and Immigration |
Apr 04
Our article is officially published:
There was a blurb about this a little while back at BPS Research Digest.
Apr 04
i’m not a fan of legends in graphs. in my mind, lines that are labeled directly are easier to read. This is done easily with directlabels package by Toby Dylan Hocking.
Just create a ggplot object and wrap it in the command directlabels().
I used it, for example, to label a plot of abortion preferences overtime by liberal-conservative self-placement.
[sourcecode language="plain"]
abortion <- na.omit(ddply(.data=data, .variables=.(year,ideology), .fun=summarise, wtd.mean=mean(x=abortion,na.rm=T,weights=vcf0009a)))
library(directlabels)
library(ggplot2)
direct.label(ggplot(abortion, aes(x = year, y = wtd.mean, colour=ideology)) + geom_line() + theme_bw() + opts(axis.title.x = theme_text(size = 12, vjust = .25)) + ylab("Support for Abortion Rights") + opts(legend.position="")+ scale_x_continuous(limits=c(1972,2015),breaks=seq(from=1972,to=2008,by=6))+xlab("Year"),"last.points")
[/sourcecode]