[R-sig-ME] lme4: qqmath.ranef.mer fails for lmer model with more than one random-effects term for a given grouping factor

[Gerrit Eichner]

Thank you very much, Maarten!

It works like a charm (and saved me a a lot of time). :-)
Also thx for the reference to the SO post.

  Best regards  --  Gerrit

---------------------------------------------------------------------
Dr. Gerrit Eichner                   Mathematical Institute, Room 212
gerrit.eichner using math.uni-giessen.de   Justus-Liebig-University Giessen
Tel: +49-(0)641-99-32104          Arndtstr. 2, 35392 Giessen, Germany
http://www.uni-giessen.de/eichner
---------------------------------------------------------------------

Am 15.05.2019 um 14:18 schrieb Maarten Jung:
> Dear Gerrit,
> 
> I encountered the same problem a while ago and wrote a custom function
> based on this [1] SO post that should work (see plot-Re.txt attached).
> 
> Best regards,
> Maarten
> 
> [1] https://stackoverflow.com/a/16511206
> 
> 
> 
> 
> On Wed, May 15, 2019 at 2:03 PM Gerrit Eichner
> <gerrit.eichner using math.uni-giessen.de> wrote:
>>
>> Dear lme4-experts,
>>
>> for an lmer model with more than one random-effects term for a
>> given grouping factor as in the following example taken from
>> qqmath.ranef.mer's help page
>>
>> fm2 <- lmer(Reaction ~ Days + (1|Subject) + (0+Days|Subject),
>>               sleepstudy)
>>
>> "caterpillar plots" of the random effects applying dotplot,
>> i.e., dotplot.ranef.mer, to the result of a call to ranef
>> with condVar = TRUE appear as expected:
>>
>> dotplot(ranef(fm2, condVar = TRUE))
>>
>>
>> But trying the analogue for the respective Q-Q plots using qqmath,
>> i.e., qqmath.ranef.mer, throws an error:
>>
>> qqmath(ranef(fm2, condVar = TRUE))
>>
>> Error in seq_len(d[1]) :
>>     argument must be coercible to non-negative integer
>> In addition: Warning message:
>> In seq_len(d[1]) : first element used of 'length.out' argument
>>
>>
>> Does anyone happen to already have a work-around for this?
>>
>> (It appears to me that the problem originates in the structure
>> of the postVar attribute of ranef(fm2, condVar = TRUE) in contrast
>> to its structure of ranef(fm1, condVar = TRUE) where fm1 <-
>> lmer(Reaction ~ Days + (Days|Subject), sleepstudy).)
>>
>> Thanks for any hints.
>>
>>    Best regards  --  Gerrit
>>
>> PS: sessionInfo()
>>
>> R version 3.5.3 (2019-03-11)
>> Platform: x86_64-w64-mingw32/x64 (64-bit)
>> Running under: Windows 10 x64 (build 17763)
>>
>> Matrix products: default
>>
>> locale:
>> [1] LC_COLLATE=German_Germany.1252  LC_CTYPE=German_Germany.1252
>> [3] LC_MONETARY=German_Germany.1252 LC_NUMERIC=C
>> [5] LC_TIME=German_Germany.1252
>>
>> attached base packages:
>> [1] stats     graphics  grDevices utils     datasets  methods   base
>>
>> other attached packages:
>> [1] ggplot2_3.1.1   lattice_0.20-38 lme4_1.1-21     Matrix_1.2-17
>>
>> loaded via a namespace (and not attached):
>>    [1] Rcpp_1.0.1       magrittr_1.5     splines_3.5.3    MASS_7.3-51.3
>>    [5] tidyselect_0.2.5 munsell_0.5.0    colorspace_1.4-1 R6_2.4.0
>>    [9] rlang_0.3.4      minqa_1.2.4      plyr_1.8.4       dplyr_0.8.0.1
>> [13] tools_3.5.3      grid_3.5.3       gtable_0.3.0     nlme_3.1-137
>> [17] withr_2.1.2      assertthat_0.2.1 lazyeval_0.2.2   tibble_2.1.1
>> [21] crayon_1.3.4     purrr_0.3.2      nloptr_1.2.1     glue_1.3.1
>> [25] labeling_0.3     compiler_3.5.3   pillar_1.3.1     scales_1.0.0
>> [29] boot_1.3-20      pkgconfig_2.0.2
>>
>>
>> ---------------------------------------------------------------------
>> Dr. Gerrit Eichner                   Mathematical Institute, Room 212
>> gerrit.eichner using math.uni-giessen.de   Justus-Liebig-University Giessen
>> Tel: +49-(0)641-99-32104          Arndtstr. 2, 35392 Giessen, Germany
>> http://www.uni-giessen.de/eichner
>>
>> _______________________________________________
>> R-sig-mixed-models using r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models