Hi,
I have a script that takes a subset of genes on a microarray and tries
to fit a coxph model to the expression values for each gene. This seems
to work fine but in some cases it produces warnings and/or errors.
For example:
Error in fitter(X, Y, strats, offset, init, control, weights = weights, :
NA/NaN/Inf in foreign function call (arg 6)
In addition: Warning message:
In fitter(X, Y, strats, offset, init, control, weights = weights, :
Ran out of iterations and did not converge
In this situation I would like to:
1) Deal with it so that it the scripts result data.frame the p value etc
are set to NA.
2) Suppress the Error and Warning messages
What is the best way to do this?
Thanks
--
**************************************************************
Daniel Brewer, Ph.D.
Institute of Cancer Research
Molecular Carcinogenesis
Email: daniel.brewer at icr.ac.uk
**************************************************************
The Institute of Cancer Research: Royal Cancer Hospital, a charitable Company
Limited by Guarantee, Registered in England under Company No. 534147 with its
Registered Office at 123 Old Brompton Road, London SW7 3RP.
This e-mail message is confidential and for use by the a...{{dropped:2}}
On Tue, Jun 17, 2008 at 9:47 AM, Daniel Brewer <daniel.brewer at icr.ac.uk> wrote:> Hi, > > I have a script that takes a subset of genes on a microarray and tries > to fit a coxph model to the expression values for each gene. This seems > to work fine but in some cases it produces warnings and/or errors. > > For example: > Error in fitter(X, Y, strats, offset, init, control, weights = weights, : > NA/NaN/Inf in foreign function call (arg 6) > In addition: Warning message: > In fitter(X, Y, strats, offset, init, control, weights = weights, : > Ran out of iterations and did not converge > > In this situation I would like to: > 1) Deal with it so that it the scripts result data.frame the p value etc > are set to NA. > 2) Suppress the Error and Warning messages > > What is the best way to do this? >Perhaps look at try() and look at the help for options() which explains different ways to handle warnings and errors.
Error in fitter(X, Y, strats, offset, init, control, weights = weights, : NA/NaN/Inf in foreign function call (arg 6) In addition: Warning message: In fitter(X, Y, strats, offset, init, control, weights = weights, : Ran out of iterations and did not converge ------- The warning message could be ignored. However, I am very interested in the error message; it is one I have not seen before. If you could recreate the data set that produces it and send it to be that would be useful. Terry Therneau (author of coxph)
Hi,
I have enclosed the data load("coxtest.rdata") to get it into R. Here
is the command line to produce the error
coxph(Surv(RecFollowUpTime,Rec)~values,data=test)
As you can see the values are almost all the same value, which is
probably causing the problem.
Dan
Terry Therneau wrote:> Error in fitter(X, Y, strats, offset, init, control, weights = weights, :
> NA/NaN/Inf in foreign function call (arg 6)
> In addition: Warning message:
> In fitter(X, Y, strats, offset, init, control, weights = weights, :
> Ran out of iterations and did not converge
>
> -------
>
> The warning message could be ignored. However, I am very interested in
the
> error message; it is one I have not seen before. If you could recreate the
data
> set that produces it and send it to be that would be useful.
>
> Terry Therneau
> (author of coxph)
>
>
--
**************************************************************
Daniel Brewer, Ph.D.
Institute of Cancer Research
Molecular Carcinogenesis
Email: daniel.brewer at icr.ac.uk
**************************************************************
The Institute of Cancer Research: Royal Cancer Hospital, a charitable Company
Limited by Guarantee, Registered in England under Company No. 534147 with its
Registered Office at 123 Old Brompton Road, London SW7 3RP.
This e-mail message is confidential and for use by the addressee only. If the
message is received by anyone other than the addressee, please return the
message to the sender by replying to it and then delete the message from your
computer and network.