hello list,
the topic is covered extensively but from none of the postings i could
conclude the correct statement for my design: a 2-level within and a 2-level
between subjects factor, both fixed, subjects as random factor.
i want to test wheter there is a within effect and if it is different for
levels of the between-factor.
i want to do it with lme and multicomp for post-hocs.
i tried
am2 <- lme(dv ~ within*between, random = ~1|subject ,data)
summary(am2)
would this be appropiate?
i'm unsure about the random term..
####data, dv is the dependent:
dat<-data.frame(list(structure(list(dv = c(1L, 3L, 2L, 2L, 2L, 5L, 3L, 4L,
3L,
5L), dvr = c(1, 6.5, 3, 3, 3, 12.5, 6.5, 10, 6.5, 12.5), subject =
structure(c(1L,
1L, 2L, 2L, 3L, 3L, 4L, 4L, 5L, 5L), .Label = c("s1", "s2", "s3",
"s4", "s5"), class = "factor"), within = c(1L, 2L, 1L, 2L, 1L,
2L, 1L, 2L, 1L, 2L), between = structure(c(1L, 1L, 1L, 1L, 1L,
1L, 2L, 2L, 2L, 2L), .Label = c("a", "b"), class = "factor")), .Names =
c("dv",
"dvr", "subject", "within", "between"), row.names = c(NA, -10L
), class = "data.frame")))
additionally i tried to run this on a rank-transformed set (dvr<-rank(dvr))
beacause of violated anova-assumptions...
any comments on general validity of the lme-model and on random term
specification would be appreciated very much (..maybe i'll have to start an
own thread on the rank-transformation)
greetings,
kay
--
View this message in context:
http://n4.nabble.com/lme-for-repeated-measures-one-within-one-between-factor-tp1583542p1583542.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
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.
