[R] Hmisc, Design, summary.Design plot- changing confidence intervals, adding color or decreasing font size

David Winsemius dwinsemius at comcast.net
Sat Jul 18 17:41:18 CEST 2009


On Jul 18, 2009, at 11:14 AM, Elizabeth Stanny wrote:

>
> Frank,
>
> I had already tried q=c(0.7,0.8,0.9,0.95) as an argument in  
> plot.summary.Design and it did not work (i.e., CIs were not  
> plotted).  Could you point me to an example using  
> plot.summary.Design that uses q as argument and has output?  I would  
> greatly appreciate it.

I am encountering an error when using any number of probabilities  
other than 5 and I think it relates to how the confbar col= defaults  
are set.

plot(s, log=TRUE, at=c(.1,.5,1,1.5,2,4,8), q=c(0.7,0.8,0.9,0.95))
Error in confbar(nbar - (i - is + 1) + 1, effect[i], se[i], q = q,  
type = "h",  :
   q and col must have same length

?confbar

  Using the example on the help page with a modified q vector of  
length 5 gives output:

  plot(s, log=TRUE, at=c(.1,.5,1,1.5,2,4,8), q = c(0.6, 0.8, 0.95,  
0.975, 0.99))

Experimentation shows that providing a col vector of the same length  
as q also succeeds:

plot(s, log=TRUE, at=c(.1,.5,1,1.5,2,4,8), q=c(0.7,0.8,0.9,0.95),  
col=gray(c(0, 0.25, 0.75, 1)))

-- 
DW

>
> Thanks.  Elizabeth
>
> Using: Hmisc_3.6-0 and Design_2.2-0
>
> ## S3 method for class 'summary.Design':
>     plot(x, at, log=FALSE,
>         q=c(0.7, 0.8, 0.9, 0.95, 0.99), xlim, nbar, cex=1, nint=10,
>         cex.c=.5, cex.t=1, clip=c(-1e30,1e30), main, ...)
>
> On Saturday, July 18, 2009, at 06:58AM, "Frank E Harrell Jr" <f.harrell at vanderbilt.edu 
> > wrote:
>> David Winsemius wrote:
>>> I am completely puzzled by this exchange, first because changing the
>>> conf.int argument _does_ affect the output of plot.Design in the
>>> expected manner,  and second, because the help page of plot.Design
>>> includes a description of conf.int as a parameter and says its  
>>> default
>>> _is_ 0.95.
>>
>> She is not using plot.Design.  She is using plot.summary.Design.
>>
>> Note that plot.summary.Design does have a related argument called q.
>>
>> Frank
>>
>>>
>>> Using Design_2.1-2    survival_2.35-4  Hmisc_3.5-2
>>>
>>
>>
>> -- 
>> Frank E Harrell Jr   Professor and Chair           School of Medicine
>>                     Department of Biostatistics   Vanderbilt  
>> University
>>
>>

David Winsemius, MD
Heritage Laboratories
West Hartford, CT




More information about the R-help mailing list