[R] Rcmdr numSummary: means of multiple variables without grouping

John Fox jfox at mcmaster.ca
Wed Nov 23 00:16:11 CET 2011


Dear Boris,

This bug is traceable to a change in the mean() function in R and is fixed in the current version (1.7-3) of the Rcmdr package on CRAN.

Best,
 John

------------------------------------------------
John Fox
Sen. William McMaster Prof. of Social Statistics
Department of Sociology
McMaster University
Hamilton, Ontario, Canada
http://socserv.mcmaster.ca/jfox/

On Tue, 22 Nov 2011 21:26:41 +0100
 "Boris Mayer" <bocaboa3 at googlemail.com> wrote:
> Hello there,
> 
>  
> 
> when using the function numSummary in Rcmdr and selecting more than one
> variable (without grouping), the grand mean across all variables is returned
> for each variable instead of the mean of each single variable. However, this
> happens only for the mean, and not for sd, quantiles and na.
> 
>  
> 
> This is the output:
> 
>  
> 
> > numSummary(dataset1 [,c("var1", "var2")], 
> 
> +   statistics=c("mean", "sd", "quantiles"), quantiles=c(0,.25,.5,.75,1))
> 
>             mean       sd  0%  25% 50% 75% 100%  n NA
> 
> var1     15.58491 4.154637 10  14  15 19.5   28 54  0
> 
> var2     15.58491 5.904053  5  10  15 18.5   30 52  2
> 
>  
> 
>  
> 
> When using a grouping variable, everything is fine:
> 
>  
> 
>  
> 
> > numSummary(dataset1 [,c("var1", "var2")], 
> 
> +   groups= dataset1$gender, statistics=c("mean", "sd", "quantiles"), 
> 
> +   quantiles=c(0,.25,.5,.75,1))
> 
>  
> 
> Variable: var1
> 
>            mean       sd 0% 25% 50% 75% 100%  n NA
> 
> male   16.57895 4.634602 10  14  16  20   28 19  0
> 
> female 16.28571 3.937538 10  14  15  18   28 35  0
> 
>  
> 
> Variable: var2
> 
>            mean       sd 0% 25% 50%  75% 100%  n NA
> 
> male   14.72222 5.442810  8  10  14 15.0   28 18  1
> 
> female 14.76471 6.213664  5  10  15 19.5   30 34  1
> 
>  
> 
>  
> 
>  
> 
> Any ideas how to get separate means for multiple variables in numSummary
> without grouping?
> 
>  
> 
> I am using R 2.14.0 and Rcmdr 1.7.2 on Windows 7 Professional.
> 
>  
> 
> Thanks in advance!
> 
>  
> 
> Boris
> 
>  
> 
>  
> 
> 
> 	[[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.



More information about the R-help mailing list