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

[Highland Statistics Ltd]

On 16/05/2012 06:00, r-sig-ecology-request at r-project.org wrote:
>
>
>               Please respond to
>                 Rich Shepard
>               <rshepard at appl-ec
>                   osys.com>
>
>
>
>
>
>
>   Recorded as a combination of both. Data were collected over ~31 years by
> different folks, analyzed by different labs, and stored in spreadsheets
> (gak!) with no standardized formatting. It's probably reasonable to assume
> that any entry of zero is really below the detection limit; if the chemical
> was actually not present it would still be below the detecion limit.
>
> Rich


There is a limit to what can be done with stats. Do you really want to 
analyse data that has been collected by different folks, labs, etc.? Any 
change over time may actually reflect a lab effect.

If you have a detection limit then you may want to consider models with 
a truncated distribution..:-)

Alain



-- 

Dr. Alain F. Zuur
First author of:

1. Analysing Ecological Data (2007).
Zuur, AF, Ieno, EN and Smith, GM. Springer. 680 p.
URL: www.springer.com/0-387-45967-7


2. Mixed effects models and extensions in ecology with R. (2009).
Zuur, AF, Ieno, EN, Walker, N, Saveliev, AA, and Smith, GM. Springer.
http://www.springer.com/life+sci/ecology/book/978-0-387-87457-9


3. A Beginner's Guide to R (2009).
Zuur, AF, Ieno, EN, Meesters, EHWG. Springer
http://www.springer.com/statistics/computational/book/978-0-387-93836-3


4. Zero Inflated Models and Generalized Linear Mixed Models with R. (2012) Zuur, Saveliev, Ieno.
http://www.highstat.com/book4.htm

Other books: http://www.highstat.com/books.htm


Statistical consultancy, courses, data analysis and software
Highland Statistics Ltd.
6 Laverock road
UK - AB41 6FN Newburgh
Tel: 0044 1358 788177
Email: highstat at highstat.com
URL: www.highstat.com
URL: www.brodgar.com