[R-sig-ME] warning glmer

[Steve Walker]

Hi Ben,

I think you should be fine.  Please see here for details:

https://stat.ethz.ch/pipermail/r-sig-mixed-models/2013q4/021151.html

Cheers,
Steve

On 2013-10-25 5:27 AM, Ben Pelzer wrote:
> Dear list,
>
> When running glmer I got a warning message:
>
> Warning in rankMatrix(X) :
>     rankMatrix(<large sparse Matrix>, method = 'tolNorm2') coerces to
> dense matrix.
>     Probably should rather use  method = 'qrLINPACK' !?
>
> With verbose=TRUE, the following output is produced:
>
> (NM) 20: f = 1.42942e+006 at    0.119639     0.45168 -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116 -2.7772 -0.00823687
> 0.0111525 0.000371882 0.000425201 2.08593   -0.804334   -0.597046
> -1.23742   0.0721005 -0.00524431  -0.0777254  -0.0455618   0.0182222
> 0.00949421 0.0178676  -0.0760966  -0.0310283  -0.0179217
> (NM) 40: f = 1.42942e+006 at    0.119639     0.45168  -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116     -2.7772
> -0.00823687   0.0111525 0.000371882 0.000425201     2.08593 -0.804334
> -0.597046    -1.23742   0.0721005 -0.00524431 -0.0777254  -0.0455618
> 0.0182222  0.00949421   0.0178676 -0.0760966  -0.0310283  -0.0179217
> (NM) 60: f = 1.42942e+006 at    0.119639     0.45168  -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116     -2.7772
> -0.00823687   0.0111525 0.000371882 0.000425201     2.08593 -0.804334
> -0.597046    -1.23742   0.0721005 -0.00524431 -0.0777254  -0.0455618
> 0.0182222  0.00949421   0.0178676 -0.0760966  -0.0310283  -0.0179217
> (NM) 80: f = 1.42942e+006 at    0.119639     0.45168  -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116     -2.7772
> -0.00823687   0.0111525 0.000371882 0.000425201     2.08593 -0.804334
> -0.597046    -1.23742   0.0721005 -0.00524431 -0.0777254  -0.0455618
> 0.0182222  0.00949421   0.0178676 -0.0760966  -0.0310283  -0.0179217
> (NM) 100: f = 1.42942e+006 at    0.119639     0.45168  -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116     -2.7772
> -0.00823687   0.0111525 0.000371882 0.000425201     2.08593 -0.804334
> -0.597046    -1.23742   0.0721005 -0.00524431 -0.0777254  -0.0455618
> 0.0182222  0.00949421   0.0178676 -0.0760966  -0.0310283  -0.0179217
> (NM) 120: f = 1.42942e+006 at    0.119639     0.45168  -0.0183788
> -0.00152183   0.0246831  -0.0123731   0.0524116     -2.7772
> -0.00823687   0.0111525 0.000371882 0.000425201
>
> The estimates of fixed and random effects look "normal", no unreasonable
> results. However, should I still be worried about the estimates found,
> given this warning message and verbose results?
>
> I updated package lme4 recently, using "Update packages" in the main
> menu. My R version is 3.0.2. Thanks for any help! Regards,
>
> Ben.
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>