[R] contrast {Design} question

From: Greg Tarpinian <sasprog474_at_yahoo.com>
Date: Sat 06 Aug 2005 - 03:00:39 EST


Sorry about the previous email, hadn't finished editing yet....

Here is some code that I have been trying to get to work:

A.quant <-
quantile(foo.frame$A,

         probs=seq(from=0.05, to=0.95, by=0.05)) B.quant <-
quantile(foo.frame$B,

         probs=seq(from=0.05, to=0.95, by=0.05)) gender <- levels(foo.frame$GENDER)

contrast.1 <-
contrast(Model.1,

         list(TREAT= 'A', A= A.quant, 
	      B = B.quant, 
              GENDER = gender),
         list(TREAT= 'D', A= A.quant, 
              B = B.quant, 
              GENDER = gender),
	 type = 'average', weights = table(gender))

My goal is to obtain a set of "average" Type II contrasts over the levels of GENDER, but not over the levels of A and B. R keeps telling me that "weights" needs to be 722 elements, but this is the total number of contrasts over all levels of A, B, and GENDER....

Any suggestions would be greatly appreciated,

      Greg



R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Sat Aug 06 03:11:48 2005

This archive was generated by hypermail 2.1.8 : Sun 23 Oct 2005 - 15:06:30 EST