Dear Allstaters,
I am doing an analysis on repeated data and I want to recalculate the
result from proc mixed (7 subjects, 4 timepoints, Hypothesis: is there a
time-effect?). Could anybody tell me the
Design Matrix (X)?
Hypothesis Matrix (L)?
Formula for the F-Test (F=4.34)?
Thx in advance!
Steffen
----
data original;
k=4;
group = 1;
input pat @@;
do time = 1 to k;
input value @@;
output;
end;
cards;
1 1.89 2.10 2.00 1.95
2 3.85 3.70 3.90 3.89
3 1.90 1.95 2.10 2.00
4 8.90 8.50 9.05 7.99
5 4.50 4.90 4.99 4.49
7 8.90 8.50 9.05 7.99
6 4.50 4.90 4.99 4.49
;
run;
proc mixed data = original;
class time;
model value = time / e3;
lsmeans time;
repeated time / sub = pat type = CS r ;
run;
quit;
---------------------------------------------------------
Dipl.-Math. Steffen Witte
Universitaet Heidelberg, Abteilung Medizinische Biometrie
Im Neuenheimer Feld 305, D-69120 Heidelberg
T: +49-(0)6221-56-4371, F: +49-(0)6221-56-4195
http://www.biometrie.uni-hd.de
[log in to unmask]
---------------------------------------------------------
|