st: sampsi

["Eurich, Dean" <deurich@ualberta.ca>]

Ok trying to do a sampsi calculation with 2 groups with 1 baseline and 1
fo=
llow-up measure. It is basically a before after analysis with a control
gro=
up. We are interested in the change score from baseline to the 8 week
follo=
w-up in predicting death for example

We have pilot data in 16 people: group 1 are healthy people; Group 2 are
pe=
ople with Luo Gerhig's disease (values are MRI scans)
Baseline MEAN Values are as follows:
Group 1 =3D0.61 (SD =3D 0.03)
Group 2 =3D 0.55 (SD =3D 0.03)

After 8 weeks we found the following MEANS:
Group 1 =3D 0.61 (SD 0.03)
Group 2 =3D 0.539 (SD 0.03)

So we have a mean change of 0.011 with a SD of change =3D 0.019

For my sample calculation I am totally confused on what to use for my m1
an=
d m2  and SD.

If I am using the -change- method:

Is it:
1) sampsi 0.61 0.55, sd1(.03) sd2(0.03) alpha(0.05) power(.80) pre(1)
post(=
1) r1(0.7) r01(0.7) method(change)

Or

2) sampsi 0 0.011, sd1(.03) sd2(0.03) alpha(0.05) power(.80) pre(1)
post(2)=
r1(0.7) r01(0.7) method(change)

Or

3) sampsi 0.55 0.539, sd1(.03) sd2(0.03) alpha(0.05) power(.80) pre(1)
post=
(2) r1(0.7) r01(0.7) method(change)

The only sample size that seems logical to me is using the second method
wh=
ere n1 and n2 =3D 53; method 1 and 3 give me values of like 2 an 1 for a
sa=
mple size.

Further, if I wanted to use an ancova as my method what would my m1, m2,
sd1, sd2, =
values be for the sampsi calculation.

So confused.

Thanks very much

Dean Eurich


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/