Displaying 2 results from an estimated 2 matches for "alpha_h".
Did you mean:
alpha_
2005 Jan 18
1
a question about linear mixed model in R
...ar all,
I have a somewhat unusual linear mixed model that I can't seem
to code in lme. It's only unusual in that one random effect is
applied only to some of the observations (I have an indicator
variable
that specifies which observations have this random effect).
The model is:
X_hijk = alpha_h + h * b_i + r_(ij) + e_hijk , where
h = 0 or 1 (indicator)
i = 1, ..., N
j = 1, ..., n_i
k = 1, ..., K
alpha is fixed, and the rest are random.
I'm willing to assume b, r, and e are mutually independent
and normal with var(b) = sigma^2_b, var(r) = sigma^2_r, and
var(e) = sigma^2.
Any...
1998 May 29
0
aov design questions
...iginal contrasts, but it isn't easy with
higher-way anova models. It looks easy in VR2 p 197-204
(BTW I have kroenecker and ginv functions if anyone wants them)
but I don't get it to work out nicely. V&R show the contrast
transformation as:
alpha_T = ginv(C_T) %*% C_H %*% alpha_H
where C_T is the contrast matrix for treatment contrasts, and C_H for
Helmert contrasts. The alpha's contain only the treatment contrast
effects, not the mean. This would leave the intercept estimate
unchanged (not right). For single factors it works to stick a
col.vector of 1s o...