Dear Joaquin,
Please keep the mailinglist in cc.
I'd rather think of the weeks being crossed with the fields than nested.
E.g. the effect of a week is probably similar on all fields. Then the model
looks like biomas~grass height +(1|Site/Field) + (1|Week). Note that
you'll need lme4 to fit that. crossed random effects are to straightforward
in nlme.
Random effects with as little as 4 or 5 levels might have unreliable
variance estimates. Keep that in mind when examining the modeloutput.
Best regards,
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature and
Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium
To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey
2015-10-05 14:00 GMT+02:00 Joaqu?n Aldabe <joaquin.aldabe at gmail.com>:
Thanks Thierry. Acutually, I collected each trap once a week, but decided
to sum the the whole content (30 days). Should I conserve the weekly
sampling? if so I guess the model could be insect biomas~grass height
+(1|Site\Field\Week) ?
Thanks again.
Joaqu?n.
2015-10-05 9:40 GMT-02:00 Thierry Onkelinx <thierry.onkelinx at inbo.be>:
Dear Joaquin
Your model seems reasonable, assuming that you measure the pitfalls only
once.
Best regards,
ir. Thierry Onkelinx
Instituut voor natuur- en bosonderzoek / Research Institute for Nature
and Forest
team Biometrie & Kwaliteitszorg / team Biometrics & Quality Assurance
Kliniekstraat 25
1070 Anderlecht
Belgium
To call in the statistician after the experiment is done may be no more
than asking him to perform a post-mortem examination: he may be able to say
what the experiment died of. ~ Sir Ronald Aylmer Fisher
The plural of anecdote is not data. ~ Roger Brinner
The combination of some data and an aching desire for an answer does not
ensure that a reasonable answer can be extracted from a given body of data.
~ John Tukey
2015-10-05 13:22 GMT+02:00 Joaqu?n Aldabe <joaquin.aldabe at gmail.com>:
Dear all, I want to see the effect of grass height on insect biomass in
a
farm close to a coastal lagoon in Uruguay. For that I chose 5 pairs of
fields. Each pair consist on a field with tall grass and the other with
short grass. Each pair of fields are close to each other, in order to
reduce the effect of soil type and other confounding variables. In each
field I installed 6 pitfall traps, separated 100 m each. I collected
insects for 30 days.
Is the following modeling approach correct?: I called Site to each field
pair (as they are geographically separated)
model=lme(insect biomass~grass height + (1|Site\Field), data)
Alternatively I thought of doing paired t-test..
Thankyou very much for your help.
Joaqu?n.
--
*Joaqu?n Aldabe*
*Grupo Biodiversidad, Ambiente y Sociedad*
Centro Universitario de la Regi?n Este, Universidad de la Rep?blica
Ruta 15 (y Ruta 9), Km 28.500, Departamento de Rocha
*Departamento de Conservaci?n*
Aves Uruguay
BirdLife International
Canelones 1164, Montevideo
https://sites.google.com/site/joaquin.aldabe
<https://sites.google.com/site/perfilprofesionaljoaquinaldabe>
[[alternative HTML version deleted]]