Dieter wrote:
>
> It would be good if you could tell us how you found out that "the random
> effects" were significant. I must have missed something here.
>
One of the models that I have fit looks like this:
> blueredminute <- read.table("/Users/sachi/Desktop/blueredminute.txt",
> header=TRUE)
> summary(blueredminute)
> fm1DD.lis <- lmList(DD~AA + BB | ID, data = blueredminute)
> coef(fm1DD.lis)
> fm1DD <-lme(DD ~ AA + BB, data = blueredminute, random = ~1 | ID, method =
> "ML")
> fm1DD
> fm2DD <- lme(DD ~ AA + BB, data = blueredminute, random = ~ AA | ID,
> method = "ML")
> fm2DD
> anova(fm1DD, fm2DD)
> fm3DD <- lme(DD ~ AA + BB, data = blueredminute, random = ~ BB | ID,
> method = "ML")
> fm3DD
> anova(fm1DD, fm3DD)
> fm4DD <- lme(DD ~ AA + BB, data = blueredminute, random = ~ AA + BB | ID,
> method = "ML")
> fm4DD
> anova(fm3DD, fm4DD)
> anova(fm2DD, fm4DD)
Where AA is one of the predictive variable (continuum variable), BB is
another predictive variable (continuum variable), DD is a dependent variable
(continuum variable), and ID is a subject ID number. ANOVA showed that fm4DD
is significantly different from fm3DD and also fm4DD is significantly
different from fm2DD, meaning that the random effects are significant.
Dieter wrote:
>
> In the slightly modified standard example coming with lme, the line
> age:SexFemale tells us that "girls grow slower".
>
> Dieter
>
> library(nlme)
> fm2 <- lme(distance ~ age * Sex, data = Orthodont, random = ~ 1)
>
> Fixed effects: distance ~ age * Sex
> Value Std.Error DF t-value p-value
> (Intercept) 16.3 0.98 79 16.7 0.000
> age 0.8 0.08 79 10.1 0.000
> SexFemale 1.0 1.54 25 0.7 0.508
> age:SexFemale -0.3 0.12 79 -2.5 0.014
>
>
I'd definitely try running the syntax. The only problem could be that my
other variables (e.g., CC) are mostly continuum and not categorical (e.g.,
Sex). Do you think that it would be a problem? If so, could you share an
example using continuum variable?
--
View this message in context:
http://www.nabble.com/How-can-we-predict-differences-in-a-slope%2C-given-that-the-random-component-was-significant--tp20984494p21013900.html
Sent from the R help mailing list archive at Nabble.com.
[[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.
