[R-sig-ME] zero-inflated counts

BXC (Bendix Carstensen) bxc at steno.dk
Wed Jul 30 12:23:06 CEST 2008


Byju,

If you look at Jim Lindsay's gnlm package at:
http://popgen.unimaas.nl/~jlindsey/rcode.html
you will find possibilities there.

The piece of code I used was something like:

pmod <- fmr( help1, dist="negative binomial",
             linear = ~ if.ddur + neuro + macro + ARB + ins1d + smoke,
                 mu =~exp(linear),
                pmu = rep(0,7),
                mix = ~ imp.aw + married + insdur + hypert + if.ddur,
               pmix = rep(0,8),
             pshape = 0 )

Hope this helps.
You can of course also use the Poisson distribution.

Best regards,
Bendix
______________________________________________

Bendix Carstensen
Senior Statistician
Steno Diabetes Center
Niels Steensens Vej 2-4
DK-2820 Gentofte
Denmark
+45 44 43 87 38 (direct)
+45 30 75 87 38 (mobile)
bxc at steno.dk   http://www.biostat.ku.dk/~bxc



Date: Tue, 29 Jul 2008 14:23:26 -0400
From: "Byju Govindan" <byjung at gmail.com>
Subject: [R-sig-ME] mixed effect modelling for zero inflated count
        data in R
To: R-sig-mixed-models at r-project.org
Message-ID:
        <49d3454c0807291123m1d2b8e50m7abdcc92e1693c98 at mail.gmail.com>
Content-Type: text/plain

Dear R users,

 Is gmmlAMDB the only option available to do mixed effect modelling for zero
inflated count data in R. Or does there exist any other option.

Thank you
 Byju



______________________________________________

Bendix Carstensen
Senior Statistician

Steno Diabetes Center
Niels Steensens Vej 2-4
DK-2820 Gentofte
Denmark
+45 44 43 87 38 (direct)
+45 30 75 87 38 (mobile)
bxc at steno.dk   http://www.biostat.ku.dk/~bxc

This e-mail (including any attachments) is intended for ...{{dropped:8}}




More information about the R-sig-mixed-models mailing list