R help - Apr 2008 - Summary statistics across factor levels

R users,

I intention is to calculate some summary statistics across factor
levels. I know that in Hmisc package there is a summary function which
produces neat summary statistics when using "cross" option. I would
like to produce similar output with N and Missing columns but produce
a data.frame. Is there any built-in function for that?

#example data
install.packages("Hmisc")
library(Hmisc)
sek <- seq(1, nrow(Indometh), 9)
Indometh$time[sek] <- NA
Indometh$timeclass <- factor(cut(Indometh$time, breaks=c(0,2,4,6,8,10)))
Indometh
with(Indometh, summary(conc ~ Subject + timeclass, method="cross"))

#similar with aggregate and reshape but no N or Missing count
i.mean <- aggregate(Indometh$conc, list(Indometh$Subject,
Indometh$timeclass), mean, na.rm=T)
i.mean.rhsp <- reshape(i.mean, v.names="x",
idvar="Group.1",
timevar="Group.2", direction="wide")
i.mean.rhsp  # N and missing columns needed

Thanks,
Lauri

Lauri Nikkinen wrote:
> R users,
> 
> I intention is to calculate some summary statistics across factor
> levels. I know that in Hmisc package there is a summary function which
> produces neat summary statistics when using "cross" option. I
would
> like to produce similar output with N and Missing columns but produce
> a data.frame. Is there any built-in function for that?
Take a look at the Hmisc summarize function.
> 
> #example data
> install.packages("Hmisc")
> library(Hmisc)
> sek <- seq(1, nrow(Indometh), 9)
> Indometh$time[sek] <- NA
> Indometh$timeclass <- factor(cut(Indometh$time, breaks=c(0,2,4,6,8,10)))
> Indometh
> with(Indometh, summary(conc ~ Subject + timeclass,
method="cross"))
If using summary I suggest summary(conc ~ Subject + cut2(time, 
c(0,2,4,6,8,10)), data=Indometh, method='cross')

Frank
> 
> #similar with aggregate and reshape but no N or Missing count
> i.mean <- aggregate(Indometh$conc, list(Indometh$Subject,
> Indometh$timeclass), mean, na.rm=T)
> i.mean.rhsp <- reshape(i.mean, v.names="x",
idvar="Group.1",
> timevar="Group.2", direction="wide")
> i.mean.rhsp  # N and missing columns needed
> 
> Thanks,
> Lauri
> 
> ______________________________________________
> 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.
> 

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

Try this:

sek <- seq(1, nrow(Indometh), 9)
Indometh$time[sek] <- NA
Indometh$timeclass <- factor(cut(Indometh$time, breaks=c(0,2,4,6,8,10)))
x <- summary(conc ~ Subject + timeclass, method="cross",
data=Indometh)
vec <- x$S
dim(vec) <- attr(x, "out.attrs")$dim
dimnames(vec) <- attr(x, "out.attrs")$dimnames
as.data.frame(vec)

On Wed, Apr 30, 2008 at 7:27 AM, Lauri Nikkinen <lauri.nikkinen@iki.fi>
wrote:
> R users,
>
> I intention is to calculate some summary statistics across factor
> levels. I know that in Hmisc package there is a summary function which
> produces neat summary statistics when using "cross" option. I
would
> like to produce similar output with N and Missing columns but produce
> a data.frame. Is there any built-in function for that?
>
> #example data
> install.packages("Hmisc")
> library(Hmisc)
> sek <- seq(1, nrow(Indometh), 9)
> Indometh$time[sek] <- NA
> Indometh$timeclass <- factor(cut(Indometh$time, breaks=c(0,2,4,6,8,10)))
> Indometh
> with(Indometh, summary(conc ~ Subject + timeclass,
method="cross"))
>
> #similar with aggregate and reshape but no N or Missing count
> i.mean <- aggregate(Indometh$conc, list(Indometh$Subject,
> Indometh$timeclass), mean, na.rm=T)
> i.mean.rhsp <- reshape(i.mean, v.names="x",
idvar="Group.1",
> timevar="Group.2", direction="wide")
> i.mean.rhsp  # N and missing columns needed
>
> Thanks,
> Lauri
>
> ______________________________________________
> R-help@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.
>


-- 
Henrique Dallazuanna
Curitiba-Paraná-Brasil
25° 25' 40" S 49° 16' 22" O

	[[alternative HTML version deleted]]