[R] code ok in unix & R2.6 , fails in windows & R 2.12

[Uwe Ligges]

You probably forgot to say that you have also different versions of the 
package installed!

I get on all platforms:

 > drm(formula = response ~ conc, data = assay.data, fct = l4())
Error in drm(formula = response ~ conc, data = assay.data, fct = l4()) :
   Cluster not specified. Use e.g. y ~ x + cluster(id)


with recent versions of R and drm.


So time to update R and all your packages on all your platforms.

Best,
Uwe Ligges



On 09.11.2010 17:26, Robert Kinley wrote:
>
> apologies for omitting the data ....
>
>
> conc response curve
> 1 50 0.7533954 1
> 2 50 0.7755960 2
> 3 50 0.8001151 3
> 4 89 0.2858031 1
> 5 89 0.2883478 2
> 6 89 0.2954936 3
> 7 158 0.4296482 1
> 8 158 0.4406220 2
> 9 158 0.4567403 3
> 10 282 0.6484347 1
> 11 282 0.6555722 2
> 12 282 0.7361552 3
> 13 501 0.9768917 1
> 14 501 0.9809505 2
> 15 501 0.9952711 3
> 16 890 1.3950000 1
> 17 890 1.3262830 2
> 18 890 1.4754281 3
> 19 1582 2.2157078 1
> 20 1582 2.2918927 2
> 21 1582 2.5538562 3
> 22 2813 3.7403291 1
> 23 2813 4.0623972 2
> 24 2813 4.1439147 3
> 25 5000 5.1405423 1
> 26 5000 5.4242582 2
> 27 5000 5.4322730 3
>
> also -
>
>  > model
> [[1]]
>
> A 'drc' model.
>
> Call:
> drm(formula = response ~ conc, data = assay.data, fct = l4())
>
> Coefficients:
> b:(Intercept) c:(Intercept) d:(Intercept) e:(Intercept)
> -1.6958 0.5089 6.9764 2629.7526
>
>
> attr(,"logScale")
> [1] TRUE
> attr(,"modelType")
> [1] "4pl"
> attr(,"method")
> [1] "drc"
> attr(,"class")
> [1] "multFit"
>
>
>
>
> *Uwe Ligges <ligges at statistik.tu-dortmund.de>*
>
> 09/11/2010 16:21
>
> 	
> To
> 	Robert Kinley <KINLEY_ROBERT at lilly.com>
> cc
> 	r-help at r-project.org
> Subject
> 	Re: [R] code ok in unix & R2.6 , fails in windows & R 2.12
>
>
> 	
>
>
>
>
>
> We cannot help since we do not have the data.
>
> Uwe
>
>
> On 09.11.2010 16:40, Robert Kinley wrote:
>  > hello ...
>  >
>  > Can anyone help me with this :
>  >
>  >
>  > In R.exe 2.6 , Unix , :-
>  >
>  > plot.data<-model[[i]]$data$conc
>  > newdata<-seq(min(plot.data),max(plot.data),by=1)
>  > model.pred<-predict(model[[i]],data.frame(newdata),interval="prediction")
>  > matpoints(newdata,model.pred[,c("Lower","Upper")],"l",col="blue",lty=1)
>  >
>  > works OK ...
>  >
>  >
>  > in Rgui 2.12 , Windows XP , same code
>  >
>  >> plot.data<-model[[i]]$data$conc
>  >> newdata<-seq(min(plot.data),max(plot.data),by=1)
>  >>
>  > model.pred<-predict(model[[i]],data.frame(newdata),interval="prediction")
>  > Error in `[.data.frame`(newdata, , 2) : undefined columns selected
>  >
>  >
>  >
>  > Robert Kinley ( 'baffled' of Berkshire )
>  >
>  >
>  >
>  > [[alternative HTML version deleted]]
>  >
>  > ______________________________________________
>  > R-help at r-project.org mailing list
>  > https://stat.ethz.ch/mailman/listinfo/r-help
>  > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
>  > and provide commented, minimal, self-contained, reproducible code.
>