Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: sampsi
"Eurich, Dean" <firstname.lastname@example.org>
Re: st: sampsi
Fri, 19 Aug 2011 13:09:37 -0600
Sorry for the confusion. We are not really interested in the longitudinal
changes over the longer term (I.e., 5 years). What we want to do do is
basically - Does very short term changes in brain function at time of
diagnosis (I.e., 8 weeks) predict 5 yr mortality. So in a sense the 8
week change score a "baseline value". We are not interested if the
patients continue to decline or not.
Hope that makes sense.
On 11-08-19 12:57 PM, "Phil Schumm" <email@example.com> wrote:
>On Aug 19, 2011, at 9:07 AM, Eurich, Dean wrote:
>> The study is really two separate studies. The first is what sample size
>>do we require to observe a 2% change in magnetic imaging brain scans for
>>controls and ALS patients over an 8 month period.
>To clarify, the calculation you originally asked about involved detecting
>a difference in the mean change (in your imaging outcome) between ALS and
>controls. IOW, it appears that you want to demonstrate that ALS patients
>on average decline faster than controls (who I presume are matched on
>age, gender, etc.). This is consistent with the baseline measurements
>you showed (where the average for the controls was higher than for those
>with ALS), but I presume you want to show/estimate the difference
>longitudinally rather than just cross-sectionally. You don't need to
>explain the rationale for doing this -- I just wanted to make sure that
>we were on the same page (your sentence above is a bit ambiguous WRT
>* For searches and help try:
* For searches and help try: