[R] weight median by count for multiple records

[John Kane]

This may do it but I have not verified the figures.

library(cwhmisc)
 by(xx[,3:4],xx[,2],function(x,y) weighted.mean(x,y))

--- On Thu, 7/30/09, Kirsten Beyer <kirsten-beyer at uiowa.edu> wrote:

> From: Kirsten Beyer <kirsten-beyer at uiowa.edu>
> Subject: [R] weight median by count for multiple records
> To: r-help at r-project.org
> Received: Thursday, July 30, 2009, 1:58 PM
> Hello everyone,
> 
> I have a .csv file with the following format:
> 
> uniqueID     SubjectID   
>   Distance_miles     Tag
> 1               
>   1001             
>       5.5         
>      3
> 2               
>   1001             
>       7         
>         1
> 3               
>   1001             
>       6.5         
>      1
> 4               
>   1001             
>       5         
>         1
> 5               
>   1002             
>       2         
>         2
> 6               
>   1002             
>       2         
>         2
> 7               
>   1002             
>       1.5         
>      2
> 8               
>   1003             
>       15         
>       2
> 9               
>   1003             
>       17         
>       2
> 10               
> 1003               
>     18           
>     2
> 
> 
> For each SubjectID, I want to calculate the median
> distance, where the
> Tag variable indicates the number of times that distance
> was recorded.
>  My final output table would be...
> 
> SubjectID   Median Distance
> 1001               
> 5.5
> 1002               
> 2
> 1003               
> 17
> 
> I have used the following script to calculate the median
> for a data
> frame where each recorded distance has its own row, and
> where temp is
> a dataframe containing each unique SubjectID and routes is
> the file I
> describe above.
> 
> for(i in 1:nrow(temp)){
> temp$mediandistance[i] <-
> median(routes$Distance_miles[routes$Subject_ID==temp$Subject_ID[i]])
> }
> 
> I am interested to know...
> (1) Is there a way to incorporate a weighted median into
> this script,
> where the weights are the number of times each distance is
> recorded?
> (2) Can I transform my current matrix into one that gives
> each
> distance its own row?
> 
> Help is much appreciated,
> Kirsten Beyer
> 
> ______________________________________________
> 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.
> 


      __________________________________________________________________
Yahoo! Canada Toolbar: Search from anywhere on the web, and bookmark your favourite sites. Download it now
http://ca.toolbar.yahoo.com.