Hi all,
Firstly excuse-me by this off-topic question.
I'm very confused to decide what is the better analysis to use.
Whem the experiments is a tradicional design of manipulative experiments, it
is easy to decide. But in natural observations is too complicated.
I have 6 farms, each farm cultives some sugarcane's varieties (maybe or not
the same varieties by farm). For each farm I make 3 transects (lines)
(replicates) crossing all varieties, and I make one collect point in each
variety.
Example:
In farm "A" I have 3 varieties and I make 3 transect, so I have 3*3 =
9
points. In each collect point all data are obtained independently.
The data are:
* production (my response)
My explanatory variables are:
* sugarcane's variety (categorical, not necessarily the same on all farms)
* age of sugarcane (continuous, not necessarily the same on all farms)
* name of farm (block ??)
* topography (categorical, not necessarily the same on all farms)
* infestation (continuous, the main explanatory variable)
I think make a modelo like this:
lm(production~variety*age*farm*topography*infestation)
My doubt is about the errors, I dont get to know if this is nested, mixed etc.
Anybody can help-me.
Thanks for all
Ronaldo
--
Short people get rained on last.
--
| //|\\ [*****************************][*******************]
|| ( ? ? ) [Ronaldo Reis J?nior ][PentiumIII-600 ]
| V [ESALQ/USP-Entomologia, CP-09 ][HD: 30 + 10 Gb ]
|| / l \ [13418-900 Piracicaba - SP ][RAM: 128 Mb ]
| /(lin)\ [Fone: 19-429-4199 r.229 ][Video: SiS620-8Mb ]
||/(linux)\ [chrysopa at insecta.ufv.br ][Modem: Pctel-onboar]
|/ (linux) \[ICQ#: 5692561 ][Kernel: 2.4.18 ]
|| ( x ) [*****************************][*******************]
||| _/ \_Powered by Gnu/Debian Woody D+:) | Lxuser#: 205366
