I seem to recall a discussion on this sometime in the last few years,
but I cannot find the message.
In GLM repeated measures one can plot the PROFILE. However, some of the
profiles are giving odd results and I am trying to track down the
problem. I am getting negative means for variables that have all values
GE zero!
Since I am under time pressure, I would like to try doing the profiles
outside GLM.
I would like a GPL approach because the .sgt file from does not seem to
keep all of the changes I make to a plot made by GLM, e.g., I label the
X-axis points
2000 2001 2002 etc., and save the chart template and make that the
default.
For each State I am trying to plot 3 lines one for each group. The line
would connect the scores for a group at each of the time points
There are 4 time points (years) for one kind of data and 5 time points
for another. These would be incompletely separate graphs.
I would like to put the year on the x-axis. I have a separate variable
for each year.
On the Y axis I would like to plot a continuous DV.
I have the data in raw form and in aggregated form.
Thanks in advance.
Art Kendall
Social Research Consultants
=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD
Art Kendall
Social Research Consultants
Locked
