Dear PLS experts,
I have a group of subjects that was given SPECT scans and a cognitive test, both at time 1 and time 2. 84 were tested at time 1, but only 48 returned to be tested at time 2.
I would like to run a behavioural PLS to see whether SPECT scans obtained at time 1 are predictive of cognitive performance at time 1 and time 2.
Given that only 48 subjects have cognitive performance at both times, am I only permitted to run a behavioural PLS on those 48, treating time as a within-subject condition?
OR, can I treat the subjects tested at different times as separate groups, and run a 2-group behavioural PLS that would associate SPECT and cognition within the 84 tested at time 1, and within the 48 tested at time 2? This latter option seems a bit dubious as it is like pretending the 2 groups are made of different subjects when in fact one is a subset of the other.
Baycrest is an academic health sciences centre fully affiliated with the University of Toronto
Privacy Statement - Disclaimer - © 1989-2024 BAYCREST HEALTH SCIENCE. ALL RIGHTS RESERVED