[R-sig-ME] Could not get a lmer or glmer summary

[Ben Bolker]

Eric Edeline <edeline at ...> writes:

> 
> Dear David,
> 
> here is the Str(m11):
> 
>  > m11<-lmer(Logl ~ 1|Species, data=Data)
>  > str(m11)
> Formal class 'mer' [package "lme4"] with 34 slots
>   ..@ env     :<environment: 0xc077a5c>
>   ..@ nlmodel : language I(x)
>   ..@ frame   :'data.frame':    92093 obs. of  2 variables:
>   .. ..$ Logl   : num [1:92093] 3.72 4.35 4.83 4.56 5.5 ...
>   .. ..$ Species: Factor w/ 50 levels "ABH","ABL","ANG",..: 20 18 32 29 
> 48 3 21 2 31 24 ...

  [snip snip snip]

  Nothing really obvious pops out.
  I know your data set is really large, but can you either post
it somewhere, or see if a subset of your data set gives you the
same problem?  If it doesn't (i.e. if you only get problems with
the full data set) maybe that will provide a hint.
 
  I made up data that looked a little bit like yours 
and didn't have a problem:

> set.seed(1001)
> Logl <- rnorm(92093)
> Species <- factor(rep(1:50,200))[1:92093]
> Data <- data.frame(Logl,Species)
> m11 <- lmer(Logl~1|Species,data=Data)
> m11
Linear mixed model fit by REML 
Formula: Logl ~ 1 | Species 
   Data: Data 
   AIC   BIC logLik deviance REMLdev
 28375 28396 -14184    28361   28369
Random effects:
 Groups   Name        Variance   Std.Dev.
 Species  (Intercept) 0.00089705 0.029951
 Residual             0.99753902 0.998769
Number of obs: 10000, groups: Species, 50

Fixed effects:
              Estimate Std. Error t value
(Intercept) -0.0003448  0.0108462  -0.032
> nrow(Data)
[1] 92093

  ... although there is one weird thing, that
"number of obs." is reported as 10000 (???)

> sessionInfo()
R version 2.10.1 (2009-12-14) 
i486-pc-linux-gnu 

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=C              LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] lme4_0.999375-32   Matrix_0.999375-38 lattice_0.18-3    

loaded via a namespace (and not attached):
[1] grid_2.10.1