Dear all,
I would be very grateful for a little advice on the above. As i
understand it, if i have 5 outcomes, i simply multiply the p-values by 5. If
i have less than 5 outcomes, i can get by with not using a multiple testing
correction. If i have 4 outcomes and within each of these, there are further
tests( 3 groups), then i can simply mutliply each p-value of the 4 outcomes
by 3 to account for the multiple testing within (rather than 12). Can i
please hear other statistcians views on this point?
Thanking you in advance
best wishes
Ian Grace
|