 |
 |
Dear all I have had an enquiry in response to a reviewer's comment on the description of the power and sample size for a single cohort study methodology (ie there is no comparator or 'unexposed' group; all a priori comparisons are made internally between subgroups). We use the sample size tables from Machin for estimates of suitable sample size when background is unknown (as is generally the case for unexpected adverse events) Specifically they query '...whether one can actually use the term 'power' in such 'exposed-only cohorts....' And also ' how do you calculate a p-value in an exposed-only cohort study'..... I'm really not sure what the point the reviewer is trying to make? Can anyone interpret their enquiry into something meaningful? Your hopefully Debbie A Non-statistician Please Note This email is private and intended for the addressee(s) only. It may contain information that is proprietary. Any dissemination, distribution or copying of information contained is unauthorised and prohibited if you are not the recipient. If you have received this message in error, please delete/destroy it. You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.