[R-sig-ME] Issue with experimental design?

[Ben Bolker]

Ted Wright <cewright at ...> writes:

> 
> You should treat this as a 3-group design. There is no nesting 
> or crossing,
> but you can still compare the outcomes for the three groups.
> 
> Ted Wright

  I agree. The way to make the distinction(s) you are interested
in (normal vs. treatment, or normal vs. low vs. treatment) is
by setting the contrasts of your fixed effects appropriately.
(You can see ?contrasts ; unfortunately setting custom contrasts
is a little bit opaque, although in your case the contr.sdif()
function from the MASS package might be helpful.)

> -----Original Message-----
> From: r-sig-mixed-models-bounces at ...
> [mailto:r-sig-mixed-models-bounces at ...] On Behalf Of Yla Savh
> Sent: Saturday, October 12, 2013 4:11 AM
> To: r-sig-mixed-models at ...
> Subject: [R-sig-ME] Issue with experimental design?
> 
> Dear forum members, Could you please help me confirm if there is a problem
> with the experimental design? There are two initial groups (vitamin D
> deficient and normal group). Then, the D deficient group has
>  two treatments
> (with a low D dosage and a high D dosage), while the normal group has only
> one treatment (maintenance therapy). 
> Initially, I thought it might be a nested design (treatment nested within
> groups, where the treatment is a fixed effect, and groups and treatment
> nested in groups are random effects. However, I do not think it is a correct
> design as the groups did not include the same treatments. Am I correct?
> I see only one solution where we will have only one or two groups and the
> same treatments should apply to each of them. Are there other
> solutions?Thanks,Julia