TY - JOUR
T1 - Conjunction group analysis
T2 - An alternative to mixed/random effect analysis
AU - Heller, Ruth
AU - Golland, Yulia
AU - Malach, Rafael
AU - Benjamini, Yoav
PY - 2007/10/1
Y1 - 2007/10/1
N2 - We address the problem of testing in every brain voxel v whether at least u out of n conditions (or subjects) considered shows a real effect. The only statistic suggested so far, the maximum p-value method, fails under dependency (unless u = n) and in particular under positive dependency that arises if all stimuli are compared to the same control stimulus. Moreover, it tends to have low power under independence. For testing that at least u out of n conditions shows a real effect, we suggest powerful test statistics that are valid under dependence between the individual condition p-values as well as under independence and other test statistics that are valid under independence. We use the above approach, replacing conditions by subjects, to produce informative group maps and thereby offer an alternative to mixed/random effect analysis.
AB - We address the problem of testing in every brain voxel v whether at least u out of n conditions (or subjects) considered shows a real effect. The only statistic suggested so far, the maximum p-value method, fails under dependency (unless u = n) and in particular under positive dependency that arises if all stimuli are compared to the same control stimulus. Moreover, it tends to have low power under independence. For testing that at least u out of n conditions shows a real effect, we suggest powerful test statistics that are valid under dependence between the individual condition p-values as well as under independence and other test statistics that are valid under independence. We use the above approach, replacing conditions by subjects, to produce informative group maps and thereby offer an alternative to mixed/random effect analysis.
KW - Combining tests
KW - Dependent contrasts
KW - False discovery rate
KW - Global null hypothesis
KW - Meta-analysis
KW - Multiple comparisons
KW - Pooled significance values
UR - http://www.scopus.com/inward/record.url?scp=34548541559&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2007.05.051
DO - 10.1016/j.neuroimage.2007.05.051
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:34548541559
SN - 1053-8119
VL - 37
SP - 1178
EP - 1185
JO - NeuroImage
JF - NeuroImage
IS - 4
ER -