[R] smooth the ecdf plots

[Frank E Harrell Jr]

Linda Lei wrote:
> Hi All,
> 
>  
> 
> I have codes as follows to get the ecdf plots:
> 
>  
> 
>  >
> day.hos2<-c(6,4,6,6,4,6,5,4,7,5,6,6,8,6,17,9,8,4,6,3,5,8,7,12,5,10,6,4,6
> ,13,7,6,6,25,4,9,96,6,6,6,6,9,4,5,5,4,10,5,7,6)
> 
>  
> 
>  >
> day.hos3<-c(5,6,7,6,4,5,6,6,6,6,19,7,5,9,8,8,7,5,6,20,40,5,8,7,7,5,6,13,
> 11,9,4,6,9,16,6,7,6)
> 
>  
> 
>  > f<-ecdf(day.hos2)
> 
>  
> 
>  > plot(f,col.p='red',col.h='red')
> 
>  
> 
>  > g<-ecdf(day.hos3)
> 
>  
> 
> 
>>lines(g,lty=2)
> 
> 
>  
> 
> But in order to compare the two ecdf plots. I want to smooth the ecdf
> plot, make it like a continuous distribution curve. Could you please
> 
> help me with it? I try to find some arguments in "plot" but not
> successful.
> 
>  
> 
> Thank you!

Think about keeping them ECDFs and not distorting them.  And you can 
superimpose two of them using thin blank lines for one and thicker gray 
scale lines for the other and be able to see them clearly.  Use e.g.

library(Hmisc)
?ecdf  (look at groups argument)

Someday I may rename ecdf in Hmisc to avoid confusion with the builtin 
ecdf function.

Frank

> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> 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
> 


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