[R] Getting the correct factor level as Dunnett control in glht()

Andrew Koeser arborkoeser at yahoo.com
Thu Feb 28 03:44:24 CET 2013

Fantastic! Thanks, Don. I saw contrMat()  and base option, but for 
whatever reason I didn't see how/if they fit together.

Your help is greatly appreciated.



On 02/27/2013 03:07 PM, MacQueen, Don wrote:
> I think you can probably specify the base level using the contrMat()
> function, which has a 'base=' argument.
> Disclaimer:
> This is a fragment from something I did recently, and is not intended to
> be reproducible by anyone else. Rather, it is intended to provide a hint
> as to how to use the contrMat() function for Andrew's key question. (so no
> side comments about posting etiquette, please)
>     fita <- aov(vv ~ tfac, data=vsub)
>     ngrp <- table(vsub$tfac)
>     cm <- contrMat(ngrp)
>     dt.lt <- glht(fita, linfct=mcp(tfac=cm), alternative='less')
> -Don

More information about the R-help mailing list