[prev in list] [next in list] [prev in thread] [next in thread] 

List:       bioconductor
Subject:    Re: [BioC] Warning message.
From:       Gordon Smyth <smyth () wehi ! edu ! au>
Date:       2004-03-31 0:12:47
Message-ID: 6.0.1.1.1.20040331101138.0292c0e0 () imaphost ! wehi ! edu ! au
[Download RAW message or body]

At 01:24 AM 31/03/2004, Johan Lindberg wrote:
>When doing
>
>corp <- duplicateCorrelation(Mmatrixp, design= designp, ndups=2, 
>spacing=32448)
>
>I got the warning message:
>
>Warning message:
>Too much damping - convergence tolerance not achievable in: glmgam.fit(dx, 
>dy, start = start, tol = tol, maxit = maxit, trace = trace)
>
>Is this something to care about

No it's not. It's probably caused by one of the individual correlations 
converging to -1, but this won't affect the overall correlation which is a 
robust average.

Gordon

>Best regards
>
>/ Johan Lindberg


[prev in list] [next in list] [prev in thread] [next in thread]