Herman Rubin wrote:
>
> In article <[EMAIL PROTECTED]>,
> Jeff <[EMAIL PROTECTED]> wrote:
> >Hello,
>
> >Would like to ask the design of experiment gurus to help me with the
> >following questions:
>
> >1. why designs for experiments should be orthogonal ?
>
> The computations get easier.
Also, the interpretation is usually more straightforward.
> >2. which problems may I encounter if I use non-orthogonal design ?
>
> The nice simple ANOVA procedures are no longer valid.
> This does not mean that nothing can be done.
You may also encounter software that analyzes the data improperly!
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================