Skip to content

R for Windows GUI front-end has encountered a problem

4 messages · Nantachai Kantanantha, Uwe Ligges

#
Hi,
I try to run my model using Quantile Regression (quantreg) package.
However, when I run the script, it has an error message in a pop-up window:

R for Windows GUI front-end has encountered a problem and needs to close.  
We are sorry for the inconvenience.

The error has error information as follows:

Error signature
AppName: rgui.exe	 AppVer: 2.21.51220.0	 ModName: r.dll
ModVer: 2.21.51220.0	 Offset: 00065e50

I am not sure what causes this problem since sometime the model is run 
through and give the result. Sometime it has an error during the way. If the 
model itself is wrong, it should not give any result but in my case, it 
gives the result but just "sometime".

If you know what causes this problem and know how to solve it, please let me 
know.

Thank you very much for your help.
Sincerely yours,
Nantachai
#
Nantachai Kantanantha wrote:

            
Please report your problem together with a small but reproducible 
example to the package maintainer (hence CC: Roger Koenker).

Uwe Ligges
3 days later
#
Hi,
Thank you very much for your reply.
The modeil is about estimating nonparametric regression parameters which 
incorporates large dimensionality compared to the number of observations.

This may cause the problem that R can run the same model just sometime, not 
always.
Is there any solution to solve this kind of problem?

Sincerely yours,
Nantachai
#
Nantachai Kantanantha wrote:

            
So is this a statistical problem correpsonding to collinearity and 
degrees of freedom rather than an R issue?
Well, at least R should not crash as reported in your former message.
Are you sure you have the most recent version (3.85) of quantreg?
Again: we (particularly Roger Koenker, if this is a bug in quantreg) 
cannot fix anything if we cannot reproduce the crash.
Therefore, please, please, please specify a reproducible example. That 
means some artificial (or real, if not too big) data and the code that 
makes R crash.

Uwe Ligges