Thanks for all of your help, David, I finally got it. Here's some generic
syntax in case it helps someone else down the road (using a 4-way ANOVA
with repeated measures on all factors):
# LOAD DATA
data <- read.table("PATH\\datafile.txt")
# RUN THE ANOVA
data.aov <- aov(y ~ factor(x1)*factor(x2)*factor(x3)*factor(x4) +
Error(factor(id)/(factor(x1)*factor(x2)*factor(x3)*factor(x4))),data)
# TO PRINT ALL MEANS BY EFFECT
print(model.tables(data.aov,"means"),digits=3)
# TO GET SEs FOR FACTOR x1
attach(data)
foo <- data.frame(tapply(y,list(id,x1),mean))
mean(foo) # ANOTHER WAY TO GET MEANS, LIMITED TO FACTOR x1
# COMPUTE SEs FOR x1
sd(foo)/sqrt(nrow(foo))
SEs for an interaction can be had by:
foo <- data.frame(tapply(y,list(id,x1,x2),mean))
sd(foo)/sqrt(nrow(foo))
David, thank you again for all of the help!
Cheers,
Jason
On Dec 13, 2008 3:15pm, David Winsemius <dwinsem...@comcast.net> wrote:
>
>
> On Dec 13, 2008, at 2:15 PM, js.augus...@gmail.com wrote:
>
>
>
>
> > Does not this give you what you need?
>
> > model.tables(rawfixtimedata.aov,"means", se=TRUE)
>
>
>
> I tried that, but get an error:
>
> SEs for type 'means' are not yet implemented
>
>
>
>
> I don't get that error. Using the example and this call
>
>
>
> model.tables(npk.aov,"means", se=TRUE)
>
>
>
> ....I get tables and then:
>
>
>
> Standard errors for differences of means
>
> block N P K N:P N:K P:K
>
> 2.779 1.604 1.604 1.604 2.269 2.269 2.269
>
> replic. 4 12 12 12 6 6 6
>
>
>
> Is your version of R current?
>
>
>
>
>
>
> Maybe I'm not using the correct terminology to describe what I need to
do. Using the main effect of Marking as an example, I have the following
mean fixation times for each of 12 subjects:
>
>
>
>
> > txt
> + 1 1278 586
>
> + 2 2410 571
>
> + 3 408 477
>
> + 4 645 371
>
> + 5 265 415
>
> + 6 4871 354
>
> + 7 1878 790
>
> + 8 6064 592
>
> + 9 761 363
>
> + 10 1073 566
>
> + 11 1043 383
>
> + 12 1170 290"
>
>
>
> > marking.t , header=TRUE, row.names="Sub")
>
> > marking.t
>
> Absent Present
>
> 1 1278 586
>
> 2 2410 571
>
> 3 408 477
>
> 4 645 371
>
> 5 265 415
>
> 6 4871 354
>
> 7 1878 790
>
> 8 6064 592
>
> 9 761 363
>
> 10 1073 566
>
> 11 1043 383
>
> 12 1170 290
>
>
>
> That list copied into R produces this pair of means
>
>
>
> > mean(marking.t)
>
> Absent Present
>
> 1822.1667 479.8333
>
>
>
>
>
>
>
>
>
>
>
>
> The means for markings present and absent, respectively, as reported by
both R and SPSS were:
>
> factor(marking)
>
> Present Absent
>
> 480 1822
>
>
>
>
>
>
>
>
>
>
>
>
>
> The standard errors for these means, SE(x) = SD(x)/sqrt(n), should be:
>
> Present Absent
>
> 41.42 525.55
>
>
>
>
> > sd(marking.t)/sqrt(nrow(marking.t))
>
> Absent Present
>
> 525.58353 41.44599
>
>
>
>
>
>
>
>
>
>
>
>
> Which is what SPSS gives. I need to know how to get R to compute the same
values.
>
>
>
> Any suggestions?
>
>
>
> Thanks,
>
>
>
> Jason
>
>
>
>
>
>
>
> >
>
> >
>
> >
>
> >
>
>
>
>
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
