R help - Feb 2011 - Plotting individual trajectories from individual growth model

Hi all,

I am trying to plot the fitted trajectories for each individual from an
individual growth model (fit with a linear mixed effects model in lme).  How
can I plot each person's trajectory in the *same* panel, along with the
mean-level trajectory?

Below is an image of a plot similar to what I'm trying to create (from:
http://jpepsy.oxfordjournals.org/content/31/10/1002/F6.large.jpg):
http://r.789695.n4.nabble.com/file/n3315494/fitted_trajectories.jpg 

Thanks so much for your help!
-- 
View this message in context:
http://r.789695.n4.nabble.com/Plotting-individual-trajectories-from-individual-growth-model-tp3315494p3315494.html
Sent from the R help mailing list archive at Nabble.com.

Hi:

These are sometimes called 'spaghetti plots'; here is a variation on an
example in the ggplot2 book by Hadley Wickham using the Oxboys data from
package nlme:

library(ggplot2)
data('Oxboys', package = 'nlme')
g <- ggplot(Oxboys, aes(x = age, y = height))
g + geom_line(aes(group = Subject)) +
      geom_smooth(aes(group = 1), colour = 'red', size = 1)

If you're not familiar with the package...
  * The first line that defines the object g sets up the 'base plot';
its
core 'aesthetics',
     or graphics elements, if you will, are the x-variable age and
y-variable height. These
     are expected to be present in every subsequent 'geom' call (think
of a
geom as a type
     of plot, although it actually refers to its geometry)
 * + denotes addition of 'layers' to the plot; we add the individual
trajectories with geom_line(),
      where group = Subject indicates that separate lines be drawn for each
subject
 * the average line (with default confidence envelope) is drawn using a
smoother (geom_smooth);
   group = 1 indicates that we want the smooth over all subjects. Additional
properties (also
   plot elements) such as color and thickness (size) are added to make the
average line
   stand out from the individual trajectories.
 * Note that variables are mapped to aesthetics, but plot elements can also
be set to fixed
   values by defining them outside aes(). This is why, for example, ggplot2
'knew' to produce
   separate lines for each subject, because the group aesthetic was mapped
to values of Subject.

For more about ggplot2, see its on-line help page at
http://had.co.nz/ggplot2   Scroll to the bottom of the page to find them.

HTH,
Dennis

On Sun, Feb 20, 2011 at 12:59 PM, dadrivr <dadrivr@gmail.com> wrote:
>
> Hi all,
>
> I am trying to plot the fitted trajectories for each individual from an
> individual growth model (fit with a linear mixed effects model in lme).
>  How
> can I plot each person's trajectory in the *same* panel, along with the
> mean-level trajectory?
>
> Below is an image of a plot similar to what I'm trying to create (from:
> http://jpepsy.oxfordjournals.org/content/31/10/1002/F6.large.jpg):
> http://r.789695.n4.nabble.com/file/n3315494/fitted_trajectories.jpg
>
> Thanks so much for your help!
> --
> View this message in context:
>
http://r.789695.n4.nabble.com/Plotting-individual-trajectories-from-individual-growth-model-tp3315494p3315494.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.
>
	[[alternative HTML version deleted]]