nested mixed effects logistic regression binomial glm) results differ by function.

Thankyou, Malcolm

This is embarrassing.  You are right, the parentheses are necessary and are in the models I ran.  I am sure I typed those parentheses, but they are not in my request any more ?  I think I know what happened.

Sorry about that. 

I am working through the other people?s suggestions, thankyou too.

Regards

Lize

 

 

From: Malcolm Fairbrother [mailto:M.Fairbrother at bristol.ac.uk] 
Sent: 24 April 2015 12:08
To: lizestats at gmail.com
Cc: r-sig-mixed-models
Subject: Re: nested mixed effects logistic regression binomial glm) results differ by function.

 

Dear Lize,

 

Does it make any difference if you try:

glmer(CC ~ predictor + (1 | area / household), family = binomial)

 ?

 

I may be wrong, but I thought the parentheses were important here.

 

 

Best wishes,
Malcolm

 

 

 

Date: Thu, 23 Apr 2015 18:16:26 +0200
From: Lize van der Merwe <lizestats at gmail.com>
To: <r-sig-mixed-models at r-project.org>
Subject: [R-sig-ME] nested mixed effects logistic regression binomial
        glm)    results differ by function.

Please advise:

I have a dichotomous outcome on 2500 individuals. From 18 geographical
areas, and many households nested within areas. I need to assess the
association between various predictors and my outcome, adjusting for the
correlation within households, as well as within areas. The following R
functions provide dramatically different results.

glmer(CC~predictor+1|area/household,family=binomial)

and

glmmPQL(CC~predictor, random=~1|area/household),family=binomial)

Why? Which is correct?

Thanks in advance.  (I posted this on another site too.)

Lize

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Dear Lize,

Does it make any difference if you try: glmer(CC ~ predictor + (1 |
area / household), family = binomial) ?

I may be wrong, but I thought the parentheses were important here.


Best wishes, Malcolm

Nice catch! It would be interesting to try to develop a test (if not
exact, at least a heuristic) that would flag these problems ...

Date: Thu, 23 Apr 2015 18:16:26 +0200

From: Lize van der Merwe <lizestats at gmail.com> To:
<r-sig-mixed-models at r-project.org> Subject: [R-sig-ME] nested
mixed effects logistic regression binomial glm)    results differ
by function.

Please advise:

I have a dichotomous outcome on 2500 individuals. From 18
geographical areas, and many households nested within areas. I
need to assess the association between various predictors and my
outcome, adjusting for the correlation within households, as well
as within areas. The following R functions provide dramatically
different results.

glmer(CC~predictor+1|area/household,family=binomial)

and

glmmPQL(CC~predictor, random=~1|area/household),family=binomial)

Why? Which is correct?

Thanks in advance.  (I posted this on another site too.)

Lize

[[alternative HTML version deleted]]

_______________________________________________ 
R-sig-mixed-models at r-project.org mailing list 
https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)

iQEcBAEBAgAGBQJVOohBAAoJEOCV5YRblxUH/NQIAI+I9NjcKGIjOU5vJZna33O9
Xp90KymCj0ZAB+Wf489nWrsIJamlUc2bixicYqf1IMGFe9KId38bggWiddL1wlzj
8twRVdTEA6YRn+lbUV6r9JNZ8g21wHVRa77PSNAQwB3TR4v4sDkn7ItkNm3kDqSF
cMgU6iYTELruut8YxBQim/SvrmSNSWypehkMMjU1q6on/KyCvvOI2torxhcEiewt
8bKyq5PpVNbglrMVYQ1giPUJa8yD+yr4vG/gK3uEUASZP/q7BS+6qLrbaqCdwtHj
wxXL6SxipUUyFdx6HLiq2jTuxtaWjCYYMLpgpW/oqtYf8EpyOBdYtFEgLEUHZtY=
=3XWS
-----END PGP SIGNATURE-----