Skip to content

Spearman's analysis

2 messages · Timmiccoop@aol.com, Jason Turner

#
I have computed correlation coefficients for my dissertation data using 
Spearman's Rho with adjustments for tie scores; however, I do not have access 
to a way to find exact p's. I have a friend who has R but he doesn't know if 
it is appropriate for my analysis, given the constraint of tie scores? Can 
you advise me? Thanks. Michele Fagan
-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://stat.ethz.ch/pipermail/r-help/attachments/20010909/1c9ce2c1/attachment.html
#
Not a full-time statistician, so I can't advise on the breakdown
of Spearman's rho under ties.  However, the library exactRankTests
might give you a good starting point on how to compute such
stats (appropriate or not) in the presence of ties.  Rnews, volume
1/1 has a nice explanation of the package, by its author:

@Article{Rnews:Hothorn:2001,
  author      = {Torsten Hothorn},
  title       = {On Exact Rank Tests in R},
  journal     = {R News},
  year        = 2001,
  volume      = 1,
  number      = 1,
  pages       = {11--12},
  month       = {January},
  url         = {http://CRAN.R-project.org/doc/Rnews/},
}
  
Cheers
  
Jason