[R] summary.formula table questions

Frank E Harrell Jr f.harrell at vanderbilt.edu
Wed Jul 5 05:46:14 CEST 2006

Matthew Harbur wrote:
> Question 1) I am using the summary.formula function, from the Hmisc,
> package, to construct a table of the mean establishment rates of multiple
> plant ecotypes.  I do not want the count (N) columns included in the table.
> Is there a way to suppress that statistic? 
> Question 2) The table will have multiple columns, each representing a
> different location. Is there a way to include Tukey's HSD at the bottom of
> each column?
> Thank you.
> Matt


For 1) where method='reverse' or 'cross' you can do
s <- summary( ... )
print(s, prn=FALSE)

For method='response' the latex.summary.formula.response method has a 
prn argument and it would not be too hard to add one to 

Your best bet for 2) is probably to use summary.formula with 
method='reverse' and to write a new 'test' function for continuous 
response variables that includes some kind of across-column summary.


> Matthew M. Harbur
> University of Minnesota Southwest Research and Outreach Center
> 23669 130th Street
> Lamberton, MN  56152
> (507) 752-5091 (office)
> (507) 752-5097 (fax)

Frank E Harrell Jr   Professor and Chair           School of Medicine
                      Department of Biostatistics   Vanderbilt University

More information about the R-help mailing list