[S] lme: standard errors of fixed effects estimates

Laffont, Jean-Louis (Laffont@phibred.com)
Wed, 2 Dec 1998 03:21:28 -0600


Dear S-Plus users,

Using S-Plus 4.5 (Win 95), I have fitted the following two-way mixed model:

Y_ij = u + alpha_ i + B_ j + E_ ij

where:
. alpha_i: fixed parameter; B_ j: random parameter
. each level of factor A is considered to have its own variance: gamma_i .

lme.res<-lme(fixed = y ~ A - 1, random = ~ 1,
cluster = ~ B, data = test.df, var.function = "strata",
var.covariate = ~ A)

and got the gamma_i using:
lme.res$sigma^2 * lme.res$delta

My question is:
How could I get standard errors of the differences between two mean
estimates for the fixed effects?

Thanks,

Jean-Louis Laffont (laffont@phibred.com)

Pioneer Genetique
Aussonne - France
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news