Quantcast

Kruskal Wallis Post hoc

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Kruskal Wallis Post hoc

jhartsho
Hi, I have searched and found a response to a question similar to mine but when I tried the code, R says it's not an actual function so I thought I'd ask here.

Cookies.csv

I have attached the data I am using.  I am trying to look at two things: how moisture content changes over time, and how it changes along the length of a log (bolt).  My data is not normal and doesn't become normal after ArcSin or Log transformations.  Because the 'Days' has 4 levels, I performed a Kruskal-Wallis (kruskal.test) and got significant results.  Same for comparing 'Cookie'.

Neither of these have only 2 levels so significance here doesn't really explain it in depth....but everything I'm finding for post hoc with a KW says Mann Whitney.  But when I try this (wilcox.test) in R it doesn't work - bc it should only have 2 levels.

Can I simply run a tukeyHSD to see differences between levels?
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Kruskal Wallis Post hoc

David Carlson
Look at kruskalmc in package pgirmess and package multcomView for plotting
the results.

----------------------------------------------
David L Carlson
Associate Professor of Anthropology
Texas A&M University
College Station, TX 77843-4352



> -----Original Message-----
> From: [hidden email] [mailto:r-help-bounces@r-
> project.org] On Behalf Of jhartsho
> Sent: Monday, June 11, 2012 2:27 PM
> To: [hidden email]
> Subject: [R] Kruskal Wallis Post hoc
>
> Hi, I have searched and found a response to a question similar to mine
> but
> when I tried the code, R says it's not an actual function so I thought
> I'd
> ask here.
>
> http://r.789695.n4.nabble.com/file/n4633035/Cookies.csv Cookies.csv
>
> I have attached the data I am using.  I am trying to look at two
> things: how
> moisture content changes over time, and how it changes along the length
> of a
> log (bolt).  My data is not normal and doesn't become normal after
> ArcSin or
> Log transformations.  Because the 'Days' has 4 levels, I performed a
> Kruskal-Wallis (kruskal.test) and got significant results.  Same for
> comparing 'Cookie'.
>
> Neither of these have only 2 levels so significance here doesn't really
> explain it in depth....but everything I'm finding for post hoc with a
> KW
> says Mann Whitney.  But when I try this (wilcox.test) in R it doesn't
> work -
> bc it should only have 2 levels.
>
> Can I simply run a tukeyHSD to see differences between levels?
>
> --
> View this message in context: http://r.789695.n4.nabble.com/Kruskal-
> Wallis-Post-hoc-tp4633035.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> [hidden email] 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.

______________________________________________
[hidden email] 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.
Loading...