[R-sig-ME] Reporting results of a mixed-effects model, using the negative binomial distribution
Célia Sofia Moreira
ce||@@o||@more|r@ @end|ng |rom gm@||@com
Thu Jan 31 15:10:13 CET 2019
Dear all,
I am with some difficulties in reporting the results of a mixed-effects
model, with the following main output:
Random effects:
Groups Name Variance Std.Dev.
Subj (Intercept) 0.1726 0.4155
Number of obs: 164, groups: Subj, 50
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.09118 0.14255 0.64 0.522
Time 0.11498 0.00515 22.33 <2e-16 ***
This is a negative binomial mixed-effects model (log link), Time is the
indep. variable, and Y is the dep. variable. I would like to know if I can
write that:
*Not accounting for the uncertainty of random effects (i.e., setting the
random effects to zero), the fixed effect of Time on Y is written on the
form:*
*exp(0.09118 + 0.11498 * Time).*
If it is not correct/rigorous, can you please suggest me how should I
report this fixed effect (setting random effects to 0)?
Best regards,
csm
[[alternative HTML version deleted]]
More information about the R-sig-mixed-models
mailing list