sylvie perera wrote:
>
> Hi,
>
> If a result is not significant, I realise this is because it may
> be due to chance.
>
> Is there a way of telling if more subjects are needed or there
> actually is no difference between the groups?
This isn't quite the right question. What you're trying to get at is
answered in part by a confidence interval for the difference between
the groups, which tells you what differences are consistent with the
data.
See my note at http://www.tufts.edu/~gdallal/ci.htm
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
