Answers are grounded in this paper and cite their sources.
Although magnitudes of memory improvement for the elderly tend to be larger for a learning skill training and a social support group compared with a waiting list group, the individual variability is sufficiently large to obscure statistical differences in the treatment effect. In our examination of individual variability in the data two possible confounding factors were uncovered: (1) low baseline performers tend to improve regardless of the treatment whereas high baseliners tend not to improve or decline in their posttest performances; (2) high verbal IQ subjects tend to perform well on all memory tests. A lesson learned in this study is that if these two variables are not equally distributed across treatment and control groups spurious results may be obtained.
No takes yet. Share an insight, caveat, or question.
Schaffer et al. (1982) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: