[R-sig-eco] Continuous (Non-Count) Skewed Data With Many Zeros

[Tom_Philippi at nps.gov]

Rich--
Are those true zeros, or below detection limit values?  My only experience
with water chemistry data had non-detects, not zeros, and I had to use the
NADA package.  On the bright side, I didn't have to worry about lots of
zeros...

Tom 2

-------------------------------------------
Tom Philippi, Ph.D.
Quantitative Ecologist
Inventory and Monitoring Program
National Park Service
Tom_philippi at NPS.gov
http://science.nature.nps.gov/im/monitor
-------------------------------------------



                                                                           
             Rich Shepard                                                  
             <rshepard at appl-ec                                             
             osys.com>                                                  To 
             Sent by:                  r-sig-ecology at r-project.org         
             r-sig-ecology-bou                                          cc 
             nces at r-project.or                                             
             g                                                     Subject 
                                       [R-sig-eco] Continuous (Non-Count)  
                                       Skewed Data With Many Zeros         
             05/15/2012 11:15                                              
             AM MST                                                        
                                                                           
                                                                           
             Please respond to                                             
               Rich Shepard                                                
             <rshepard at appl-ec                                             
                 osys.com>                                                 
                                                                           
                                                                           




   The water chemistry data of metal concentrations are not normally
distributed (based on Q-Q plots) and are not improved by transformation
(log10, sqrt, cubic root). For the 30 metal species the percentage of zeros
ranges from none (10 metals) to 48.6; average 5.6. Most metals are at very
low concentrations with infrequent spikes which might be very high.

   Those with fewer zeros are not a concern, but I'd like your thoughts on
1)
at what percentage do the number of zeros become a concern and 2) how to
characterize and model these data.

Rich

_______________________________________________
R-sig-ecology mailing list
R-sig-ecology at r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-ecology