[R] summary of linear fixed effects model is different than the HSAUR book

Christopher W. Ryan cryan at binghamton.edu
Mon Jul 23 00:33:53 CEST 2007


Running R 2.5.1 and a newly downloaded lme4 package on WinXP

I'm trying to work my way through Everitt and Hothorn's "Handbook of
Statistical Analyses Using R," c 2006.  (No, it's not homework.)

Chapter 10 discusses linear mixed effects models for longitudinal data.
 I've called my long data frame BtheB.long

Here's the model from the book, which I run.
lmer1 <- lmer(bdi ~ bdi.pre + months + treatment + drug + length + (1 |
subject), data = BtheB.long, method = "ML", na.action = na.omit)

Here is the summary of the model that I see:

> summary(lmer1)
Linear mixed-effects model fit by maximum likelihood
Formula: bdi ~ bdi.pre + months + treatment + drug + length + (1 | subject)
   Data: BtheB.long
  AIC  BIC logLik MLdeviance REMLdeviance
 1885 1910 -935.3       1871         1866
Random effects:
 Groups   Name        Variance Std.Dev.
 subject  (Intercept) 48.299   6.9498
 Residual             25.129   5.0128
number of obs: 280, groups: subject, 97

Fixed effects:
               Estimate Std. Error t value
(Intercept)     5.94372    2.24915   2.643
bdi.pre         0.63819    0.07759   8.225
months         -0.71703    0.14606  -4.909
treatmentBtheB -2.37311    1.66368  -1.426
drugYes        -2.79786    1.71993  -1.627
length>6m       0.25639    1.63213   0.157

Correlation of Fixed Effects:
            (Intr) bdi.pr months trtmBB drugYs
bdi.pre     -0.678
months      -0.264  0.023
tretmntBthB -0.389  0.121  0.022
drugYes     -0.071 -0.237 -0.025 -0.323
length>6m   -0.238 -0.242 -0.043  0.002  0.158


But on page 169, summary() is shown to produce additional columns in the
"fixed effects" section, namely degrees of freedom and the P-value (with
significance stars).

How can I produce that output?  Am I doing something wrong?  Has lme4
changed?

Thanks.

-- 
Christopher W. Ryan, MD
SUNY Upstate Medical University Clinical Campus at Binghamton
40 Arch Street, Johnson City, NY  13790
cryanatbinghamtondotedu
PGP public keys available at http://home.stny.rr.com/ryancw/

"If you want to build a ship, don't drum up the men to gather wood,
divide the work and give orders. Instead, teach them to yearn for the
vast and endless sea."  [Antoine de St. Exupery]



More information about the R-help mailing list