Hi folks
I am using the lmer function (in the lme4 library) to analyse some data where
individuals are clustered into sets (using the SetID variable) with a single
fixed effect (cc - 0 or 1). The lmer model and output is shown below.
Whilst the fixed effects are consistent with stata (using xtmixed, see below),
the std dev of the random effect for SetID is very very small
(3.5803e-05)compared to stata's (see below 1.002). Any ideas why this should be
happening please....?
LMER MODEL
summary(lmer(AnxietyScore ~ cc + (1|SetID), data=mydf))
Linear mixed model fit by REML
Formula: AnxietyScore ~ cc + (1 | SetID)
Data: mydf
AIC BIC logLik deviance REMLdev
493.4 503.4 -242.7 486.6 485.4
Random effects:
Groups Name Variance Std.Dev.
SetID (Intercept) 1.2819e-09 3.5803e-05
Residual 1.3352e+01 3.6540e+00
Number of obs: 90, groups: SetID, 33
Fixed effects:
Estimate Std. Error t value
(Intercept) 3.1064 0.5330 5.828
cc 2.3122 0.7711 2.999
Correlation of Fixed Effects:
(Intr)
cc -0.691
STATA XTMIXED
xtmixed anxietyscore cc || setid:, reml
Mixed-effects REML regression Number of obs = 90
Group variable: setid Number of groups = 33
Log restricted-likelihood = -242.48259 Prob > chi2 = 0.0023
------------------------------------------------------------------------------
anxietyscore | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
cc | 2.289007 .7492766 3.05 0.002 .8204519 3.757562
_cons | 3.116074 .5464282 5.70 0.000 2.045094 4.187053
------------------------------------------------------------------------------
------------------------------------------------------------------------------
Random-effects Parameters | Estimate Std. Err. [95% Conf. Interval]
-----------------------------+------------------------------------------------
setid: Identity |
sd(_cons) | 1.002484 .797775 .2107137 4.769382
-----------------------------+------------------------------------------------
sd(Residual) | 3.515888 .3281988 2.928045 4.22175
------------------------------------------------------------------------------
with thanks & best wishes
M
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
