I'm using lmer to fit mixed-effect logistic regression models. This
is for a small data set.
First, I fit a constant:
Generalized linear mixed model fit using Laplace
Formula: propm ~ (1 | study)
Data: inducedSR71507.dat
Family: binomial(logit link)
AIC BIC logLik deviance
183.7 189.4 -89.84 179.7
Random effects:
Groups Name Variance Std.Dev.
study (Intercept) 0.035812 0.18924
number of obs: 127, groups: study, 21
Estimated scale (compare to 1 ) 1.028571
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.11256 0.04979 2.261 0.0238 *
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
So far, so good.
Next, I fit a model with a fixed effect:
Generalized linear mixed model fit using Laplace
Formula: propm ~ 1 + c.age + (1 | study)
Data: inducedSR71507.dat
Family: binomial(logit link)
AIC BIC logLik deviance
5339 5348 -2667 5333
Random effects:
Groups Name Variance Std.Dev.
study (Intercept) 0.44094 0.66404
number of obs: 127, groups: study, 21
Estimated scale (compare to 1 ) 314587114
Fixed effects:
Estimate Std. Error z value Pr(>|z|)
(Intercept) 0.058093 1.033273 0.05622 0.955
c.age 0.007262 0.095393 0.07613 0.939
That is one heck of a large scale parameter!
I would be glad to be shown what I am doing wrong, but I am thinking
that this is a bug......
study is entered as a factor in the data frame.
here is the session info
> sessionInfo()
R version 2.5.1 (2007-06-27)
i386-apple-darwin8.9.1
locale:
en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
attached base packages:
[1] "stats4" "stats" "graphics"
"grDevices" "utils"
"datasets" "methods" "base"
other attached packages:
mlmRev lme4 MASS Matrix lattice nlme
"0.995-1" "0.99875-4" "7.2-34"
"0.999375-0" "0.15-11" "3.1-83"
Any and all help is very much appreciated!
--
Steven Orzack
The Fresh Pond Research Institute
173 Harvey Street
Cambridge, MA. 02140
617 864-4307
www.freshpond.org
[[alternative HTML version deleted]]
