[R] Which skewness does pelpe3() from package "lmom" use?

[frauke]

Hi everyone, 

I was trying to fit a Log Pearson III distribution through some maxima data.
I got thrown off because my results in Excel (using a frequency factor
table) are different from my results using pelpe3() in the R-package "lmom".
The only reason I can think of is the skewness. 

The Pearson III distribution has three parameters: Location (mean), scale
(standard deviation) and shape (skewness). The command pelpe3() returns the
same values for the first two parameters like I had computed in Excel.
However, the skewness is much higher. 

Excel uses the type II skewness. *Does anybody know what type of skewness
pelpe3() uses and why?*

To be complete, I included some data. 
data.txt <http://r.789695.n4.nabble.com/file/n4673984/data.txt>  
This table gives the the maximum daily rainfall for each of 22 years. I want
to fit the distribution through those maximum rainfall events. These are the
parameters that I generated for the Pearson III distribution in Excel and R:

		                       * Excel     R*
*location	(mean)	*        0.68	     0.68
*shape	(skewness)	      *1.04	     *1.6*
*scale	(stand dev)*	0.38     0.4

Any help would be greatly appreciated!

Thank you!

Frauke







--
View this message in context: http://r.789695.n4.nabble.com/Which-skewness-does-pelpe3-from-package-lmom-use-tp4673984.html
Sent from the R help mailing list archive at Nabble.com.