s-news
[Top] [All Lists]

Random effects in summary lme

To: <s-news@lists.biostat.wustl.edu>
Subject: Random effects in summary lme
From: "Jimenez-Leal William" <william.jimenezleal@lsc.gov.uk>
Date: Tue, 13 Nov 2007 15:55:04 -0000
In-reply-to: <1D98C2C866C7D34DB400A10594D55E810585D9E8@E2K3VS02.lsc.local>
Thread-index: Acgh62xbhKxjM+22TsudFkdRJIDcUwEG4E/wAAFKULAAAEE/0A==
Thread-topic: Random effects in summary lme

 

Dear S plus users,

 

I am fitting a bunch of mixed effects logistic regressions using glmmPQL and I have a little problem extracting their random coefficients. I am modeling the probability of passing an exam against student's prior attainment, allowing the latter to vary randomly across schools. Looks something like this

 

a<-glmmPQL(POINTS~PA +PA2+PA3,random=~PA|INST, family=binomial(link=logit), data="" niter=1000)

 

('pa' is the prior attainment, 'inst' is school)

 

Normally, I just produce a summary of this object, which gives you the corresponding standard deviations and correlations, and work out the variance-covariance matrix from there. This is the summary:

 

summary(a)

Linear mixed-effects model fit by maximum likelihood

 Data: k

       AIC      BIC    logLik

  18142.24 18189.96 -9063.118

 

Random effects:

 Formula:  ~ PA | INST

 Structure: General positive-definite

                StdDev   Corr

(Intercept) 3.68174225 (Intr)

    PA      0.09902275 0.253

   Residual 0.60168538      

 

Variance function:

 Structure: fixed weights

 Formula:  ~ invwt

 

(Etc, etc)

Number of Observations: 2881

Number of Groups: 142

 

 

The problem is that when I extract this matrix from the summary object directly, the random effects numbers do not match.

 

summary(a)$modelStruct$reStruct

 

Random effects:

 Formula:  ~ PA | INST

 Structure: General positive-definite

               StdDev   Corr

(Intercept) 6.1190489 (Intr)

     PRIORC 0.1645756 0.253

   Residual 1.0000000

 

 

Would anyone tell me what I am missing here? Clearly, the matrix is being transformed when summarized, but why and how?

 

Thanks a lot for your help

 

William

Confidentiality and Disclaimer: This email and its attachments are intended for the addressee
only and may be confidential or the subject of legal privilege.
If this email and its attachments have come to you in error you must take no action based on
them, nor must you copy them, distribute them or show them to anyone.
Please contact the sender to notify them of the error.
This email and any attached files have been scanned for the presence of computer viruses.
However, you are advised that you open any attachments at your own risk.
Please note that electronic mail may be monitored in accordance with the Telecommunications
(Lawful Business Practices)(Interception of Communications) Regulations 2000.
<Prev in Thread] Current Thread [Next in Thread>