John,
Thanks for your reply! I will check again I must have missed it!
~Nicole Ford
Ph.D. Student
Graduate Assistant/ Instructor
Department of Government and International Affairs
University of South Florida
office: SOC 012M
e: nmhicks at mail.usf.edu
http://gia.usf.edu/student/nford/
Sent from my iPhone
On Mar 31, 2013, at 7:54 PM, John Fox <jfox at mcmaster.ca> wrote:
Dear Nicole,
Thanks to Sandy Weisberg, who is a coauthor of the package, the effects
package has methods for objects produced by lme() in the nlme package and
lmer() and glmer() in the lme4 package, to plot the fixed effects. See
?effect.
I hope this helps,
John
-----Original Message-----
From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
project.org] On Behalf Of Nicole Ford
Sent: Sunday, March 31, 2013 7:27 PM
To: r-help-r-project.org help
Subject: [R] lmer effects-type plot?
hello, all.
while i have a mcmc running, i am looking at the frequestist method of
my model. i have never done HLM so i am looking for ways to plot them
that might yeild something useful like dr. fox's effects plot package.
this is my model, where dem is democracy ranked continuous 1:10, trsut
is a 3 level categorical variable, cpi is 1:10, etc...
hier.jags2.mod <- lmer(dem ~ trust*cpi + age + gender + educ + income
+ (1 + trust | country), data=wvsAB)
i have tried the following:
tmp <- as.data.frame(confint(glht(.hier.jags2.mod))$confint)
tmp$Comparison <- rownames(tmp)
q<-(ggplot(tmp, aes(x = Comparison, y = Estimate, ymin = lwr, ymax =
upr, srt = 45)) + geom_errorbar() + geom_point())
q + theme(axis.text.x=theme_text(angle=-45))
as well as some function using xyplot to little avail, as well as a few
others i happened upon online...
any suggestions of packages/ sample code would be helpful.