Quote:
Originally Posted by Luke
I agree with Jay. There are going to be cross-over duplications in both the Uzit and BL460 Pop Reports. There's no reason to assume that one of the two backs would have more phantom cards in the report than the other........
A 40% difference is definitely statistically significant in this case.
|
Actually the greater the population, the greater chance of error - so I would argue that whatever error rate you want to work with, in absolute terms means more errors in the Uzits due to a larger population.
I agree a 40% difference is statistically significant.