Dear friends that work on spatial Ecology,
I am proceeding with the analysis of a dataset on the spatial structure of
canopy openness in the southern Brazilian mixed conifer-hardwood forests, and
would like to ask your opinion on a rather simple matter on which I have doubts.
I have six one-hectare plots subdivided in 100 10 x 10 m plots each. In the
centre of each subplot we took a hemispherical photograh and estimated canopy
openness. In Legendre and Fortin (1989) it is said that before examining each
significant value in a correlogram, we must first perfom a global test, since
several tests are done at the same time, for a given overall significance
level. The global test is made by checking whether the correlogram contains at
least one value which is significant after a Bonferroni correction.
So I ask:
1) When we have more than one correlogram (say, six) between Moran's I and
distance classes, should we adjust the significance level to account for the
fact that we are performing not only, e.g., ten significance tests within each
correlogram (which are the distance classes), but also more than one
correlogram? If yes, then the Bonferroni correction should be the significance
level divided by which value? 60 (6 correlograms x 10 classes within each
correlogram)? I guess this means that if we have a really large data set almost
nothing would be significant!
I could not find this particular information in Dale et al. (2002) nor
in Legendre and Legendre (1998), although I suspect that it is present in this
last reference, because it is rather large and my search has not been
exhaustive.
2) One of the six plots has been hit by a microtornado a few years ago, which
damaged a rather small area, 0,25 ha. So in this area we have only 25 10 x 10 m
plots. Again, according with Legendre and Fortin (1989) I should not perform
the spatial autocorrelation analysis mentioned above, because there would be
too few pairs of localities, not enough to produce significant results. I ask:
is this true even if we divide the distance classes in a irregular manner, so
that they have equal frequencies of numbers of pairs of points? If this would
allow "to compute valid coefficients even in the right-hand part of the
correlogram", it may allow valid coefficients in the middle of a correlogram
with fewer classes?
Dear friends, thank you very much for your attention!
Sincerely,
Alexandre
Dr. Alexandre F. Souza
Programa de Pós-Graduação em Biologia: Diversidade e Manejo da Vida Silvestre
Universidade do Vale do Rio dos Sinos (UNISINOS)
Av. UNISINOS 950 - C.P. 275, São Leopoldo 93022-000, RS - Brasil
Telefone: (051)3590-8477 ramal 1263
Skype: alexfadigas
[EMAIL PROTECTED]
http://www.unisinos.br/laboratorios/lecopop
--
Esta mensagem foi verificada pelo sistema de antivírus e
acredita-se estar livre de perigo.
