I am trying to draw a plot like Matlab does: The upper extreme whisker represents 95% of the data; The upper hinge represents 75% of the data; The median represents 50% of the data; The lower hinge represents 25% of the data; The lower extreme whisker represents 5% of the data. It looks like: --- 95% | | ------- 75% | | |-----| 50% | | | | ------- 25% | --- 5% Anyone can give me some hints as to how to draw a boxplot like that? What function does it? I tried boxplot() but couldn't figure it out. If it's boxplot(), what arguments should I pass to the function? Thank you for your help. I'd appreciate it. Larry
1) The boxplot in R does the 25%, 50% and 75% mark as you want
2) Check out the range argument in boxplot. I think you can redefine
your 5% and 95% quantile in terms of IQR for symmetric distribution and
hence use this feature.
However I find it easier to calculate these numbers manually and feed it
into bxp() function. Here is one such function (with lots of room for
improvement).
matlab.boxplot <- function(m){
m <- as.matrix(m)
bp <- boxplot(data.frame(m), plot=FALSE)
bp$stats <- apply( m, 2, function(x)
quantile(x, c(0.05,0.25, 0.5, 0.75, 0.95), na.rm=T) )
tmp <- apply( m, 2, function(x){
under <- x[ which( x < quantile(x, 0.05, na.rm=T) ) ]
over <- x[ which( x > quantile(x, 0.95, na.rm=T) ) ]
return( c(under, over) )
}) # always a matrix in this case
bp$out <- c(tmp)
bp$group <- rep(1:ncol(tmp), each=nrow(tmp))
bxp(bp)
}
Some usage examples :
matlab.boxplot( rnorm(50) ) # a vector
my.mat <- matrix( rnorm(300), nc=3 )
matlab.boxplot( my.mat ) # a matrix
Regards, Adai
On Sun, 2005-07-10 at 18:10 -0500, Larry Xie wrote:> I am trying to draw a plot like Matlab does:
>
> The upper extreme whisker represents 95% of the data;
> The upper hinge represents 75% of the data;
> The median represents 50% of the data;
> The lower hinge represents 25% of the data;
> The lower extreme whisker represents 5% of the data.
>
> It looks like:
>
> --- 95%
> |
> |
> ------- 75%
> | |
> |-----| 50%
> | |
> | |
> ------- 25%
> |
> --- 5%
>
> Anyone can give me some hints as to how to draw a boxplot like that?
> What function does it? I tried boxplot() but couldn't figure it out.
> If it's boxplot(), what arguments should I pass to the function? Thank
> you for your help. I'd appreciate it.
>
> Larry
>
> ______________________________________________
> R-help at 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
>
Just an addendum on the philosophical aspect of doing this. By selecting the 5% and 95% quantiles, you are always going to get 10% of the data as "extreme" and these points may not necessarily outliers. So when you are comparing information from multiple columns (i.e. boxplots), it is harder to say which column contains more extreme value compared to others etc. Regards, Adai On Sun, 2005-07-10 at 18:10 -0500, Larry Xie wrote:> I am trying to draw a plot like Matlab does: > > The upper extreme whisker represents 95% of the data; > The upper hinge represents 75% of the data; > The median represents 50% of the data; > The lower hinge represents 25% of the data; > The lower extreme whisker represents 5% of the data. > > It looks like: > > --- 95% > | > | > ------- 75% > | | > |-----| 50% > | | > | | > ------- 25% > | > --- 5% > > Anyone can give me some hints as to how to draw a boxplot like that? > What function does it? I tried boxplot() but couldn't figure it out. > If it's boxplot(), what arguments should I pass to the function? Thank > you for your help. I'd appreciate it. > > Larry > > ______________________________________________ > R-help at 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 >